Wireless charging suspension platform adaptive to power requirement of underwater equipment

Abstract

The invention provides a wireless charging suspension platform adaptive to power requirements of underwater equipment. The wireless charging suspension platform comprises a non-metal cover plate, a transmission pad and a plurality of transmitting coil layers arranged between the non-metal cover plate and the transmission pad from top to bottom, a plurality of transmitting coil groups are uniformly distributed on each transmitting coil layer, the transmitting coil groups of the adjacent transmitting coil layers are arranged in a staggered manner, and the transmitting coil group in the lower transmitting coil layer covers a gap and an edge area between the adjacent transmitting coil groups in the upper transmitting coil layer. And each transmitting coil group comprises a plurality of transmitting coils which are arranged in a tiled manner. By reasonably designing coil parameters in the transmitting coil layer, electromagnetic fields at different positions of the designed underwater wireless charging suspension platform are stable and reliable, suspension charging requirements of different underwater devices can be met, and the working capacity of an underwater wireless charging base station is improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of underwater wireless charging, and particularly relates to a wireless charging mooring platform that adapts to the power requirements of underwater equipment. Background Art

[0002] Underwater wireless charging is usually based on the principles of electromagnetic induction or magnetic resonance. To meet a wide range of power output requirements, underwater wireless charging systems usually have the ability to dynamically adjust the output power to adapt to the actual power requirements of underwater equipment in real time. However, the design of the underwater wireless charging mooring area with wide power output not only needs to consider the dynamic adjustment of the output power, but also needs to pay attention to the distribution of the electromagnetic field intensity in the area. The distribution of the electromagnetic field intensity is affected by factors such as the shape of the coil and the coil layout. In order to eliminate the influence of the foregoing factors, one of the traditional methods is to use alignment control to solve the problem. However, this method requires the design of an accurate control system and a mechanical transmission device, with a high overall manufacturing cost, and the response time may be long when adjusting the coil alignment. Especially when the equipment moves relatively fast, it cannot ensure that the control system can track in real time. Another method is to dynamically adjust the coil layout. This method requires a high-precision positioning system, otherwise it will affect the accuracy of the coil layout. At the same time, a flexible control mechanism is required to adjust the coil position in real time, which increases the complexity and debugging difficulty of the wireless charging system, and frequent adjustment of the coil layout may increase the energy consumption of the wireless charging system and affect the charging efficiency. Summary of the Invention

[0003] The purpose of the present invention is to solve the problems in the existing output power adaptive adjustment method of underwater wireless charging systems, which require the design of a complex control system or a positioning system, and have low power adjustment efficiency or affect the energy consumption of the wireless charging system, and to provide a wireless charging mooring platform that adapts to the power requirements of underwater equipment.

[0004] The technical solution adopted by the present invention is as follows:

[0005] A wireless charging mooring platform that adapts to the power requirements of underwater equipment, comprising a non-metallic cover plate, a transmission pad, and a plurality of transmitting coil layers arranged from top to bottom between the non-metallic cover plate and the transmission pad;

[0006] A plurality of transmitting coil groups are evenly distributed on a single transmitting coil layer, and the transmitting coil groups of adjacent transmitting coil layers are arranged staggeredly, and the transmitting coil groups in the lower transmitting coil layer cover the gaps and edge regions between adjacent transmitting coil groups in the upper transmitting coil layer;

[0007] A single transmitting coil group includes a plurality of transmitting coils arranged flatly.

[0008] Further, each of the single transmitting coil groups includes two pairs of transmitting coils that are laid flat and symmetrically distributed, and each pair of transmitting coils includes a first transmitting coil and a second transmitting coil that are connected in series with opposite polarities.

[0009] Further, the first transmitting coil and the second transmitting coil are circular coils, and the coil wire spacing is set at equal intervals.

[0010] Further, the transmitting coil layer is obtained according to the following design method:

[0011] Step 1: Establish a model of the transmitting coil layer of the wireless charging mooring platform, obtain several sets of data on the design schemes of the transmitting coil layer. Each design scheme includes the design parameters of the transmitting coil layer, as well as the maximum output power and energy transmission efficiency of the wireless charging mooring platform; and preprocess each set of data to divide it into training set data, validation set data, and test set data;

[0012] Among them, the design parameters of the transmitting coil include coil wire diameter, number of coil turns, outer diameter of the coil, coil wire spacing, spacing between adjacent transmitting coils, spacing between adjacent transmitting coil groups, and the number of transmitting coil groups.

[0013] Step 2: Construct a neural network model, and set the model parameters and training parameters of the neural network model; the neural network model includes an input layer, a hidden layer, an activation function, and an output layer; the neural network model is used to output the corresponding design parameters of the transmitting coil layer according to the input maximum output power of the wireless charging mooring platform and the energy transmission efficiency.

[0014] Step 3: Use the data on the design schemes of the transmitting coil layer obtained in Step 1 to train and predict the constructed neural network model, and judge the prediction effect;

[0015] Step 4: Obtain the range of the maximum power demand of the underwater equipment, and determine the maximum output power of the wireless charging mooring platform according to the range of the maximum power demand of the underwater equipment;

[0016] Input the maximum output power of the wireless charging mooring platform and the set energy transmission efficiency between the transmitting coil end of the wireless charging mooring platform and the receiving coil end of the underwater equipment into the trained and predicted neural network model to obtain the design parameters of the transmitting coil layer of the wireless charging mooring platform to be designed.

[0017] Further, in Step 2, the model parameters of the neural network model include network weights, biases, and the number of hidden layers; the training parameters include the learning rate, batch size, and number of training rounds.

[0018] Further, Step 3 includes the following steps:

[0019] Step 3.1: Input the training set data into the constructed neural network model for training, and perform real-time verification through the validation set data during the training process to monitor the training process and control the convergence effect of the neural network model training;

[0020] Step 3.2: Input the test set data into the trained neural network model for prediction, and output the optimized design parameters of the transmitting coil layer;

[0021] After prediction, compare the prediction results with the design parameters of the transmitting coil layer in the corresponding solution in Step 1, calculate the mean absolute error of each design parameter, and determine whether the mean absolute error of each parameter is less than the set error threshold. If so, complete the training and prediction of the neural network model; otherwise, return to Step 2 to readjust the model parameters and network training parameters of the neural network model.

[0022] Further, in Step 3.3, the set error threshold is 0.01.

[0023] The advantages of the present invention are as follows:

[0024] 1. In the wireless charging mooring platform of the present invention, multiple transmitting coil layers are designed. The coil groups of adjacent transmitting coil layers are arranged staggeredly, and the coil group in the lower layer covers the gaps and edge regions between the coil groups in the upper transmitting coil layer, avoiding the electromagnetic field blind areas in the charging mooring areas with multi-coil distribution, so that there is a strong electromagnetic field at any position of the mooring platform, and underwater equipment can be charged as needed at any position of the mooring platform, expanding the working range of the underwater wireless charging base station and improving the working ability of the underwater wireless charging base station.

[0025] 2. The present invention optimizes the design of parameters such as the layout method of the transmitting coil layer, the size of the transmitting coil, the number of turns of the collar, the wire diameter, the spacing between the transmitting coil groups, and the number of transmitting coil groups in the wireless charging mooring platform through numerical simulation and the method based on the neural network model, so that the electromagnetic fields at different positions of the designed underwater wireless charging base station mooring platform are stable and reliable, and can meet the mooring charging requirements of different underwater equipment.

[0026] The additional aspects and advantages of the present invention will be partly given in the following description, partly will become obvious from the following description, or will be understood through the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] The above and / or additional aspects and advantages of the present invention will become obvious and easy to understand from the description of the embodiments in conjunction with the following drawings, wherein:

[0028] Figure 1 is the overall schematic diagram of the wireless charging mooring platform for adapting to the power requirements of underwater equipment of the present invention;

[0029] Figure 2 is a layout schematic diagram of the transmitting coil layer in the present invention;

[0030] Figure 3 is a layout schematic diagram of the transmitting coil group in a single transmitting coil layer of the present invention;

[0031] Figure 4 is Figure 3 a structural schematic diagram of a single coil group in;

[0032] Figure 5 is an optimized design flow chart of the transmitting coil layer in the present invention.

[0033] In the figure: 1 - mooring platform, 2 - non - metallic cover plate, 3 - transmission pad, 4 - transmitting coil layer, 5 - transmitting coil group, 501 - first transmitting coil, 502 - second transmitting coil, 6 - underwater equipment receiving coil end. Specific embodiments

[0034] The following details the embodiments of the present invention. The described embodiments are exemplary and are intended to explain the present invention, and should not be construed as limiting the present invention.

[0035] Referring to Figures 1 - 3 , an embodiment of the present invention provides a wireless charging mooring platform adaptable to the power requirements of underwater equipment, which is used to dock with the planar underwater equipment receiving coil end 6 for wireless charging. The mooring platform 1 includes a non - metallic cover plate 2, a transmission pad 3, and multiple layers of transmitting coil layers 4 arranged from top to bottom between the non - metallic cover plate and the transmission pad. The non - metallic cover plate 2 is arranged on the top of the transmitting coil layer to protect the transmitting coil layer and the transmission pad. A plurality of transmitting coil groups 5 are evenly distributed on a single transmitting coil layer, and the transmitting coil groups of adjacent transmitting coil layers are arranged staggeredly, and the transmitting coil groups in the lower - layer transmitting coil layer cover the gaps and edge regions between the transmitting coil groups in the upper - layer transmitting coil layer, so that a strong electromagnetic field exists at any position of the mooring platform, ensuring uniform coverage of the electromagnetic field intensity in the mooring platform area.

[0036] Referring to Figure 4 , a single transmitting coil group 5 includes two pairs of symmetrically distributed coils, and each pair includes two disk - shaped coils connected in series with opposite polarities, namely the first transmitting coil 501 and the second transmitting coil 502. Connecting the first reflecting coil 501 and the second transmitting coil 502 with opposite polarities in series helps to eliminate the induced voltage between adjacent coils, reduces the unnecessary mutual interference between coils, improves the overall stability and charging efficiency of the wireless charging system, and can reduce the influence of the induced voltage on other coils, optimize the balance of power transmission, helps to reduce electromagnetic interference, improve the electromagnetic compatibility of the wireless charging system, and reduce the influence of noise on other electronic devices of the underwater equipment.

[0037] Referring to Figure 5 , the parameter optimization design process of the transmitting coil layer in the wireless charging and mooring platform of the present invention is as follows:

[0038] Step 1: Establish a model of the transmitting coil layer of the wireless charging and mooring platform. Based on simulation or experiment, generate several sets of design schemes for the transmitting coil layer. Each design scheme includes the optimized design parameters of the transmitting coil layer, the maximum output power of the wireless charging and mooring platform, and the energy transmission efficiency. The optimized design parameters of the transmitting coil include the coil wire diameter, the number of coil turns, the outer diameter of the coil, the coil wire pitch, the spacing between adjacent transmitting coils, the spacing between adjacent transmitting coil groups, and the number of transmitting coil groups.

[0039] Perform data preprocessing on the optimized design parameters of the transmitting coil layer in each design scheme. In order to ensure the training effect of the neural network in the later stage, it is necessary to standardize or normalize all the optimized design parameters of the transmitting coil to form an input data set. The output of the neural network model is the maximum output power of the wireless charging and mooring platform and the energy transmission efficiency.

[0040] Divide the input data into training set data, validation set data, and test set data, where 70% is the training set, 15% is the validation set, and 15% is the test set. The training set and the validation set are used to train the neural network model, and the test set is used to input to the trained neural network, input to the trained neural network model, and judge the accuracy of the constructed neural network model according to the predicted results of the output.

[0041] Step 2: Build a neural network model, which includes an input layer, a hidden layer, an activation function, and an output layer. Among them, the input layer is set with two output nodes, namely the maximum output power of the wireless charging stationary platform and the energy transmission efficiency, and the optimized design parameters of the transmitting coil layer are used as the output layer. Since the coil design of the wireless charging system usually has a relatively complex non-linear relationship, multiple hidden layers are required to capture more complex patterns. In this embodiment, the number of hidden layers is 3 to 5 layers. In this embodiment, ReLU (Rectified Linear Unit) is used as the activation function of the hidden layer. The neural network model outputs the corresponding optimized design parameters of the transmitting coil layer according to the input maximum output power of the wireless charging stationary platform and the energy transmission efficiency. At the same time, set the model parameters and training parameters of the network model. The model parameters include network weights, biases, and the number of hidden layers. The network weights are set using a random initialization method, such as using a normal distribution. The bias is initialized to a small constant, such as 0 or a value close to 0. During the training process, the network weights and network biases are automatically updated according to the training data and the loss function in the neural network model through the backpropagation algorithm. In this embodiment, the network training parameters include the learning rate, batch size, and number of training epochs. The initial learning rate is generally set between 0.001 and 0.1. For the optimized design of multiple coil parameters in this embodiment, the learning rate starts from 0.001. During the training process, the adaptive learning rate Adam algorithm is used to adjust the learning rate corresponding to each coil design parameter. The batch size is the number of samples used in one iteration. Considering the possible number of samples, convergence speed, and reliability of the solution, for the optimization of multiple coil parameters involved in this case, it is considered to start from 64 and adjust according to the model convergence situation and performance. In this embodiment, the number of training epochs is set to 1000, and an early stopping mechanism is set to ensure that the training of the neural network model stops when the performance on the validation set no longer improves, preventing overfitting.

[0042] Step 3: Use the transmitting coil layer design scheme obtained in Step 1 to train and predict the constructed neural network model, and judge the prediction effect. The specific contents are as follows:

[0043] Step 3.1: Input the training set data into the constructed neural network model for training, and perform real-time verification through the validation set data during the training process to monitor the training process, control the training convergence effect of the neural network model, and avoid overfitting.

[0044] During the training process, if the training loss continuously decreases and the validation loss continuously increases, it means that the constructed neural network model has memorized the training data but is not good at processing new input data. Therefore, in order to avoid this overfitting phenomenon, real-time verification is performed using the validation set data during the training process.

[0045] Step 3.2: Input the test set data obtained in Step 1 into the trained neural network model for prediction, and output the predicted optimized design parameters of the transmitting coil layer.

[0046] After prediction, compare the prediction results with the optimized design parameters of the transmitting coil layer in the corresponding solution of Step 1, calculate the mean absolute error of each design parameter, and determine whether the mean absolute error of each parameter is less than the set error threshold. If so, complete the training and prediction of the neural network model; otherwise, return to Step 2 to readjust the model parameters and network training parameters of the neural network model.

[0047] Taking the wire diameter as an example, after prediction, the neural network model outputs the corresponding predicted wire diameter. Calculate the absolute wire diameter error of each solution based on the predicted wire diameter and the wire diameter value in the corresponding solution of Step 1, and then calculate the mean absolute error based on the calculated absolute wire diameter error of each solution. Finally, compare the mean absolute error with the set error threshold. In the embodiment of the present invention, the set error threshold is 0.01.

[0048] Step 4: First, obtain the maximum power demand range of the underwater equipment, and determine the maximum output power of the wireless charging mooring platform according to the maximum power demand range of the underwater equipment; then set the energy transfer efficiency between the transmitting coil end and the receiving coil end of the underwater equipment of the wireless charging mooring platform to ensure that the energy loss is minimized at any position within the wireless charging mooring platform and ensure stable charging.

[0049] Input the maximum output power of the wireless charging mooring platform and the set energy transfer efficiency into the trained and predicted neural network model to obtain the design parameters of the transmitting coil layer of the wireless charging mooring platform to be designed.

[0050] As described above, the above is only the specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of various equivalent modifications or substitutions, and these modifications or substitutions should all be covered within the protection scope of the present invention.

Claims

1. A wireless charging and suspension platform that is adaptive to the power requirements of underwater equipment, characterized in that: It includes a non-metallic cover plate, a transmission pad, and a plurality of transmitting coil layers arranged from top to bottom between the non-metallic cover plate and the transmission pad; A plurality of transmitting coil groups are evenly distributed on a single transmitting coil layer, the transmitting coil groups of adjacent transmitting coil layers are arranged in a staggered manner, and the transmitting coil groups in the lower transmitting coil layer cover the gaps and edge areas between adjacent transmitting coil groups in the upper transmitting coil layer; A single transmitting coil group includes a plurality of transmitting coils arranged in a tiled manner.

2. The wireless charging and stopping platform according to claim 1, characterized in that: A single transmitting coil group includes two pairs of transmitting coils that are laid out flat and symmetrically distributed, and each pair of transmitting coils includes a first transmitting coil and a second transmitting coil that are connected in series and have opposite polarities.

3. The wireless charging and stopping platform according to claim 2, characterized in that: The first transmitting coil and the second transmitting coil are circular coils, and the coil line spacing is set at an equal interval.

4. The wireless charging and stopping platform according to any one of claims 1 to 3, characterized in that: The transmitting coil layer is obtained according to the following design method: Step 1: Establish a transmitting coil layer model of the wireless charging and parking platform, and obtain several sets of transmitting coil layer design scheme data. Each design scheme includes the transmitting coil layer design parameters and the maximum output power and energy transmission efficiency of the wireless charging and parking platform; And pre-process the data of each scheme to obtain training set data, validation set data and test set data; The transmitting coil design parameters include coil wire diameter, coil turns, coil outer diameter, coil wire pitch, spacing between adjacent transmitting coils, spacing between adjacent transmitting coil groups, and the number of transmitting coil groups. Step 2: Construct a neural network model and set the model parameters and training parameters of the neural network model; the neural network model includes an input layer, a hidden layer, an activation function and an output layer; the neural network model is used to output the corresponding transmitting coil layer design parameters according to the input maximum output power and energy transmission efficiency of the wireless charging suspension platform; Step 3: Use the transmitting coil layer design data obtained in step 1 to train and predict the constructed neural network model, and determine the prediction effect; Step 4: Obtain the maximum power requirement range of the underwater equipment, and determine the maximum output power of the wireless charging stop platform according to the maximum power requirement range of the underwater equipment; The maximum output power of the wireless charging moratorium platform and the energy transmission efficiency between the transmitting coil end of the wireless charging moratorium platform and the receiving coil end of the underwater equipment are input into the trained and predicted neural network model to obtain the design parameters of the transmitting coil layer of the wireless charging moratorium platform.

5. The wireless charging and stopping platform according to claim 4, characterized in that: In step 2, the model parameters of the neural network model include network weights, biases and the number of hidden layers; the training parameters include learning rate, batch size and training rounds.

6. The wireless charging and stopping platform according to claim 4, characterized in that: The step 3 comprises the following steps: Step 3.1: input the training set data into the constructed neural network model for training, and perform real-time verification through the verification set data during the training process to monitor the training process and control the convergence effect of the neural network model training; Step 3.2: input the test set data into the trained neural network model for prediction, and output the predicted optimized design parameters of the transmitting coil layer; Step 3.3: After prediction, compare the prediction result with the design parameters of the transmitting coil layer in the corresponding scheme of step 1, calculate the mean absolute error of each design parameter, and determine whether the mean absolute error of each parameter is less than the set error threshold. If so, the training and prediction of the neural network model are completed; otherwise, return to step 2 and readjust the model parameters and network training parameters of the neural network model.

7. The wireless charging and stopping platform according to claim 6, characterized in that: In step 3.3, the error threshold is set to 0.01.

Images