Wireless charging method for uncertain sensor node position

Abstract

The embodiment of the invention provides a wireless charging method for uncertain sensor node positions, and is applied to the technical field of wireless rechargeable sensor networks. The method comprises the following steps: actively detecting sensor node and obstacle distribution based on a transmitting coil array of the mobile charging equipment; a magnetic wave beam vector is formed by independently adjusting the voltage of each coil, and the accurate position of a node and the contour of an obstacle are determined by combining impedance measurement and wave beam intersection positioning; discretizing the region, constructing a vertex visible graph and generating a collision-free path complete graph; and calling a TSP solver to generate an initial charging path by taking minimization of movement consumption as a target, inputting the initial charging path to the trained reinforcement learning model, dynamically optimizing a track and a charging plan through real-time interaction, outputting an optimal path, and issuing the optimal path to the charging equipment. In this way, the problem of selecting a proper charging point in a complex scene with obstacles and uncertain node positions can be solved, accurate positioning of the nodes is achieved, and the charging efficiency is remarkably improved.

Description

Technical Field

[0001] The present disclosure relates to the field of control technology, and further to the field of wireless rechargeable sensor network technology, and in particular to a wireless charging method with uncertain sensor node locations. Background Art

[0002] In practical application scenarios, Wireless Rechargeable Sensor Networks (WRSNs) face many complex challenges. On the one hand, the location of sensor nodes is often uncertain. During the deployment process, due to environmental constraints or human factors, the actual location of the node may deviate from the pre-planned location. In addition, in some dynamic environments, such as monitoring scenarios of moving objects, the location of sensor nodes may change over time. This uncertainty in node location brings great difficulties to charging path planning. Traditional charging strategies based on fixed node locations are difficult to apply, which may cause charging devices to be unable to accurately find nodes for charging, thereby reducing charging efficiency.

[0003] On the other hand, there are usually various obstacles in WRSNs, such as buildings, trees, large equipment, etc. These obstacles will interfere with the propagation of electromagnetic waves and affect the effect of wireless charging. When planning the charging path, the mobile charging device needs to avoid these obstacles, otherwise it may cause communication interruption between the charging device and the sensor node or reduce the charging efficiency. At the same time, the presence of obstacles will also complicate the visibility between sensor nodes, further increasing the difficulty of charging path planning. Summary of the Invention

[0004] The present disclosure provides a method for wireless charging with uncertain sensor node locations, which solves the technical problem of how to select a suitable charging point in complex WRSNs scenarios with obstacles and uncertain node locations.

[0005] According to a first aspect of the present disclosure, a wireless charging method is provided in which the position of a sensor node is uncertain. The method comprises:

[0006] The transmitting coil array based on the mobile charging device preliminarily detects the distribution of each sensor node and obstacles in the wireless sensor network;

[0007] determining the precise position of each detected sensor node by individually adjusting the voltage of each coil in the transmitting coil array;

[0008] Discretize the area where the wireless sensor network is located into N grid sub-areas, construct a visible graph using grid vertices to represent sensor nodes and obstacles, and generate a complete graph of collision-free paths on the visible graph based on the vertex visibility principle; wherein N is a positive integer;

[0009] Invoking a TSP solver to minimize the movement consumption of the mobile charging device, determine the charging order of the sensor nodes, and generate an initial charging path for the mobile charging device;

[0010] The initial charging path is input into the trained reinforcement learning model to generate an optimal charging path, and a charging task is issued to the mobile charging device based on the optimal charging path.

[0011] According to the above aspects and any possible implementation manner, an implementation manner is further provided, wherein the method further includes:

[0012] Based on the trained reinforcement learning model, the energy distribution of the mobile charging device during the charging task is dynamically adjusted, and the remaining energy of the mobile charging device is monitored in real time. If the remaining energy is lower than the preset threshold, the mobile charging device is controlled to interrupt the charging task and return to the base station.

[0013] According to the above aspects and any possible implementation, an implementation is further provided, wherein the training step of the reinforcement learning model includes:

[0014] The reinforcement learning model is trained based on the position information of each sensor node in the wireless sensor network, the distribution of obstacles, the state transition information of the mobile charging device, and the charging path of the mobile charging device.

[0015] According to the above aspects and any possible implementation manner, an implementation manner is further provided, wherein determining the precise position of each detected sensor node by individually adjusting the voltage of each coil in the transmitting coil array includes:

[0016] Forming M magnetic beamforming vectors by individually adjusting the voltage of each coil in the transmitting coil array, wherein M is a positive integer;

[0017] determining a direction from an estimated center of the transmit coil array to each sensor node based on the M magnetic beamforming vectors;

[0018] The uncertainty area of ​​each sensor node is determined based on the common coverage area of ​​the M magnetic beamforming vectors, and the center of gravity of the area is used as the precise position of each sensor node.

[0019] According to the above aspects and any possible implementation, further provided is an implementation, wherein forming M magnetic beamforming vectors by individually adjusting the voltage of each coil in the transmitting coil array includes:

[0020] Apply a certain voltage to any coil in the transmitting coil array and measure the corresponding loop current. Calculate the total impedance of the receiving coil relative to the transmitting coil based on the ratio of voltage to current.

[0021] Calculating the load impedance based on the difference between the total impedance and the inherent impedance of the circuit, and then determining the magnetic channel parameters of the transmitting coil;

[0022] The transmitting coil magnetic beamforming vector is generated based on the complex conjugate of the magnetic channel parameter, and the above steps are repeated until M magnetic beamforming vectors are formed.

[0023] According to the above aspect and any possible implementation, an implementation is further provided, wherein the obstacle distribution is determined by:

[0024] By analyzing the reflection, refraction and absorption characteristics of electromagnetic waves on obstacles, the location and shape of obstacles can be identified.

[0025] According to the aspects described above and any possible implementation method, an implementation method is further provided, where when the number of sensor nodes existing in any grid sub-area exceeds a preset threshold, all sensor nodes existing in the grid sub-area are regarded as virtual nodes, and the node position with the largest receiving power is selected among the virtual nodes as the charging target point.

[0026] According to a second aspect of the present disclosure, a control method for a mobile wireless charging vehicle is provided, wherein the optimal charging path generated by any of the above methods is used to control the operation of the mobile wireless charging vehicle.

[0027] According to a third aspect of the present disclosure, an electronic device is provided, comprising: a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the above method when executing the program.

[0028] According to a fourth aspect of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored. When the program is executed by a processor, the method according to the first aspect and / or the second aspect of the present disclosure is implemented.

[0029] In this disclosure, the distribution of sensor nodes and obstacles is actively detected through the transmitting coil array of a mobile charging device. A magnetic beam vector is formed by individually adjusting the voltage of each coil, and the precise location of the node and the outline of the obstacle are determined by combining impedance measurement and beam intersection positioning. The region is discretized, a vertex visibility graph is constructed, and a complete collision-free path graph is generated. A TSP solver is called to minimize mobile consumption to generate an initial charging path and input it into a trained reinforcement learning model. The trajectory and charging plan are dynamically optimized through real-time interaction, and the optimal path is output and sent to the charging device. This solves the technical problem of how to select a suitable charging point in complex WRSNs scenarios with uncertain obstacles and node positions, improves charging efficiency and sensor node positioning accuracy in wireless sensor networks, and enables accurate and reliable charging of sensor nodes in the network in complex environments.

[0030] It should be understood that the contents described in the Summary of the Invention section are not intended to limit the key or important features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] The above and other features, advantages, and aspects of the various embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. The accompanying drawings are provided for a better understanding of the present disclosure and do not constitute a limitation of the present disclosure. In the accompanying drawings, the same or similar reference numerals represent the same or similar elements, among which:

[0032] Figure 1 A flowchart of a wireless charging method with uncertain sensor node locations provided by an embodiment of the present disclosure is shown;

[0033] Figure 2 A structural diagram of an exemplary electronic device capable of implementing an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0034] To make the purpose, technical solutions, and advantages of the embodiments of the present disclosure more clear, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments of the present disclosure, all other embodiments obtained by ordinary technicians in this field without making any creative efforts are within the scope of protection of the present disclosure.

[0035] In this document, the term "and / or" simply describes a relationship between related objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A exists alone, A and B exist simultaneously, or B exists alone. Furthermore, the character " / " in this document generally indicates that the related objects are in an "or" relationship.

[0036] In this disclosure, the distribution of sensor nodes and obstacles is actively detected through the transmitting coil array of a mobile charging device. A magnetic beam vector is formed by individually adjusting the voltage of each coil, and the precise location of the node and the outline of the obstacle are determined by combining impedance measurement and beam intersection positioning. The region is discretized, a vertex visibility graph is constructed, and a complete collision-free path graph is generated. A TSP solver is called to minimize mobile consumption to generate an initial charging path and input it into a trained reinforcement learning model. The trajectory and charging plan are dynamically optimized through real-time interaction, and the optimal path is output and sent to the charging device. This solves the technical problem of how to select a suitable charging point in complex WRSNs scenarios with uncertain obstacles and node positions, improves charging efficiency and sensor node positioning accuracy in wireless sensor networks, and enables accurate and reliable charging of sensor nodes in the network in complex environments.

[0037] Magnetic resonance coupling (MRC), a highly efficient medium-range energy transmission technology, has demonstrated tremendous potential in wireless charging sensor networks in recent years. A significant advantage of MRC lies in its ability to penetrate non-metallic obstacles or surfaces, enabling effective charging even when sensor nodes are hidden or obscured. Using MRC for node location not only allows for the detection of camouflaged or obscured nodes, but also improves charging efficiency in complex environments.

[0038] This disclosure primarily uses a mobile charging device with a transmitting coil array containing multiple transmitting coils to wirelessly charge sensor nodes. Using beamforming technology, the charging device can precisely focus the magnetic field on the receiving coil, significantly reducing spatial coupling limitations and increasing the flexibility of MRC technology. Compared to conventional wireless charging methods, beamforming technology offers significant advantages in improving node positioning accuracy and charging efficiency, providing a new technical path for the development of wireless charging sensor networks.

[0039] The present disclosure provides a wireless charging method for uncertain sensor node locations, which is applied to a wireless rechargeable sensor network system. The system includes a base station, sensor nodes, and a mobile charging device. The mobile charging devices are multiple, and the base station has multiple charging points that can charge one or more mobile charging devices at the same time.

[0040] A wireless charging method with uncertain sensor node positions provided by an embodiment of the present disclosure will be described in detail below with reference to the accompanying drawings through specific embodiments.

[0041] Figure 1 FIG. 1 shows a flow chart of a wireless charging method for uncertain sensor node positions provided by an embodiment of the present disclosure, as shown in FIG. Figure 1 As shown, a wireless charging method 100 without determining the position of a sensor node may include the following steps:

[0042] S110 , preliminarily detecting the distribution of each sensor node and obstacles in the wireless sensor network based on the transmitting coil array of the mobile charging device.

[0043] Exemplarily, the mobile charging device is equipped with a multi-coil transmitting array for transmitting low-power detection radio waves, and preliminarily marks the distribution areas of each sensor node and obstacle in two-dimensional / three-dimensional space by receiving the reflected signal strength and phase shift.

[0044] In some embodiments, the obstacle distribution is determined by:

[0045] By analyzing the reflection, refraction and absorption characteristics of electromagnetic waves on obstacles, the location and shape of obstacles can be identified.

[0046] For example, obstacle distribution is determined by the mobile charging device actively collecting environmental information during the positioning task. The transmitting coil array carried by the mobile charging device uses magnetic resonance coupling technology to emit electromagnetic waves. These electromagnetic waves are not only used to identify and locate sensor nodes, but also to detect obstacles along the path. By analyzing the reflection, refraction, or absorption characteristics of the electromagnetic waves, the mobile charging device can identify the location and shape of obstacles. This information is used to construct the topology of the environment, in which the locations of nodes and obstacles are accurately mapped onto a two-dimensional plane.

[0047] Exemplarily, the obstacles include static obstacles and dynamic obstacles.

[0048] S120 , determining the precise position of each detected sensor node by individually adjusting the voltage of each coil in the transmitting coil array.

[0049] In some embodiments, M magnetic beamforming vectors are formed by individually adjusting the voltage of each coil in the transmitting coil array; wherein M is a positive integer;

[0050] determining a direction from an estimated center of the transmit coil array to each sensor node based on the M magnetic beamforming vectors;

[0051] The uncertainty area of ​​each sensor node is determined based on the common coverage area of ​​the M magnetic beamforming vectors, and the center of gravity of the area is used as the precise position of each sensor node.

[0052] In some embodiments, forming M magnetic beamforming vectors by individually adjusting the voltage of each coil in the transmit coil array includes:

[0053] Apply a certain voltage to any coil in the transmitting coil array and measure the corresponding loop current. Calculate the total impedance of the receiving coil relative to the transmitting coil based on the ratio of voltage to current.

[0054] Calculating the load impedance based on the difference between the total impedance and the inherent impedance of the circuit, and then determining the magnetic channel parameters of the transmitting coil;

[0055] The transmitting coil magnetic beamforming vector is generated based on the complex conjugate of the magnetic channel parameter, and the above steps are repeated until M magnetic beamforming vectors are formed.

[0056] For example, due to the magnetic coupling between the transmitting coil and the receiving coil, the transmitting coil array can calculate the total impedance of the receiving coil relative to each transmitting coil by measuring the voltage-current ratio; specifically, a known voltage is applied to the kth transmitting coil. While keeping the other coils open, the current in the circuit is then measured. Capture the total impedance Z of the receive coil relative to each transmit coil K :

[0057]

[0058] in, is the inherent impedance of the TX circuit.

[0059] When the transmitting coil and receiving coil resonate:

[0060]

[0061] Among them, C and L are capacitance and inductance respectively.

[0062] The load z′ applied by the receiving coil to the kth transmitting circuit is directly measured by subtracting the inherent impedance of the circuit from the total impedance of the receiving coil relative to each transmitting coil. k , from which we can get the load and mutual inductance coefficient M on the kth TX coil k Relationship:

[0063]

[0064] Then calculate the magnetic channel m corresponding to the kth transmitting coil k :

[0065]

[0066] Where ω is the AC frequency of the transmitter, j is the imaginary unit, R L and z L Represent the resistance of the sensor and the impedance of the receiving circuit, M k is the mutual inductance coefficient.

[0067] And through m k Calculate the magnetic beamforming vector β k :

[0068]

[0069] in, is the magnetic channel m k The complex conjugate of .

[0070] Exemplarily, by using magnetic resonance coupling technology, the voltage of each coil in the transmitting coil array is adjusted to optimize the magnetic beamforming vectors. These vectors indicate the direction from the estimated center of the transmitting coil array to each sensor node. By analyzing the common coverage area of ​​multiple magnetic beamforming vectors, the uncertainty area of ​​the node position can be determined, and the center of gravity of the area is assumed to be the estimated position of the node.

[0071] After initially estimating the position of the sensor node, the relative position between the transmitting coil and the receiving coil is calibrated to ensure precise alignment of energy transfer. This process enhances the accuracy of node positioning, thereby improving the efficiency and reliability of the wireless charging system. Through this method, effective positioning and charging can be achieved even when the node position is uncertain or difficult to directly observe.

[0072] Therefore, the direction relationship between the k-TX and RX coils is:

[0073]

[0074] Among them, θ k is the angle, M || is the magnetic flux under ideal conditions.

[0075] In order to calculate the energy of wireless transmission while locating the sensor node, the transmission current Derive the received energy E in time slot τ L for:

[0076]

[0077] Where ω is the angular frequency, β k is the complex conjugate of the magnetic beamforming vector, R L and z LThey represent the resistance of the sensor and the impedance of the receiving circuit respectively.

[0078] It can be seen that the energy received by the node will change with the change of the magnetic beam, and the change of the magnetic beam will be affected by the change of the position or direction of the mobile charger. Magnetic beamforming can increase the energy transmission distance and flexibility.

[0079] S130, discretizing the area where the wireless sensor network is located into N grid sub-areas, constructing a visible graph using grid vertices to represent sensor nodes and obstacles, and generating a complete graph of collision-free paths on the visible graph based on the vertex visibility principle; wherein N is a positive integer.

[0080] For example, in order to quickly determine the appropriate charging location, the entire network area is divided into multiple grid sub-areas (ζ1, ζ2, ...) with equal side length σ. The charging positions in the same sub-area are considered to be equivalent, which means that the charging power transmitted by the mobile charging device in the area remains unchanged; then, the influence of obstacles in the spatial discretization method is considered. If there is an obstacle in the grid, the grid is considered impassable. It is worth noting that due to the coupling effect, the charging of mobile charging devices is much less affected by obstacles than traditional RF charging, which means that mobile charging devices can penetrate most obstacles and provide power to nodes. Even if the obstacle material is metal, the coil frequency can be adjusted to minimize adverse effects.

[0081] For example, a finite number of charging locations can be obtained based on the discretized grid area. To maximize charging energy, that is, to solve the MCE problem, the optimal charging route for mobile charging devices must be determined while taking into account the presence of obstacles. First, based on the node location and environmental obstacle information provided by the RLS algorithm, it is observed that the exact location of the charging stop point of the mobile charging device does not necessarily coincide with the charging stop point provided by GPS, and may even exceed the effective charging range, causing the charging mechanism to fail. By using the grid space discretization method, the shape of the obstacle can be regularized, thereby conveniently constructing a visible graph with vertices representing obstacles and temporary stops. Subsequently, based on the visibility principle between vertices, a collision-free charging path is calculated on this visible graph, resulting in a complete graph of the MC charging travel path. Using the TSP solver, the solution to the ETSPO problem in this complete graph can be obtained.

[0082] In some embodiments, when the number of sensor nodes in any grid sub-area exceeds a preset threshold, all sensor nodes in the grid sub-area are regarded as virtual nodes, and the node position with the largest receiving power is selected from the virtual nodes as the charging target point.

[0083] For example, in order to solve the problem of invalid charging caused by the failure of multi-node positioning, multiple nodes in the grid sub-area are regarded as virtual nodes, and the positioning method is performed on the virtual nodes to obtain the charging position where the multiple nodes have the maximum receiving power. In this case, beamforming is abandoned to charge the virtual nodes. According to the derivation of the effective distance in the formula, the distance between multiple nodes is relatively close. Therefore, the reduction in charging efficiency caused by this method is acceptable.

[0084] S140 , calling a TSP solver to determine the charging sequence of the sensor nodes with the goal of minimizing the movement consumption of the mobile charging device, and generating an initial charging path for the mobile charging device.

[0085] S150: Input the initial charging path into the trained reinforcement learning model to generate an optimal charging path, and issue a charging task to the mobile charging device based on the optimal charging path.

[0086] In some embodiments, the training step of the reinforcement learning model includes:

[0087] The reinforcement learning model is trained based on the position information of each sensor node in the wireless sensor network, the distribution of obstacles, the state transition information of the mobile charging device, and the charging path of the mobile charging device.

[0088] For example, during reinforcement learning model training, parameters include sensor node location information, obstacle distribution, mobile charger state transition information, energy consumption model, charging efficiency model, reward function, charging path and scheduling strategy, time slot and space discretization parameters, and model hyperparameters. These parameters together form the foundation of model training, enabling the model to adapt to dynamic changes in the environment, such as the addition of new nodes or the movement of obstacles. Through continuous trial and error and learning, the model optimizes its decision-making strategy to achieve efficient charging and positioning in uncertain and dynamic environments. Ultimately, it outputs operational decisions, including the optimal charging path, to maximize charging energy utility.

[0089] In some embodiments, the method further comprises:

[0090] Based on the trained reinforcement learning model, the energy distribution of the mobile charging device during the charging task is dynamically adjusted, and the remaining energy of the mobile charging device is monitored in real time. If the remaining energy is lower than the preset threshold, the mobile charging device is controlled to interrupt the charging task and return to the base station.

[0091] For example, charging and positioning tasks differ in resource consumption and time sensitivity, and may be affected by dynamic changes in the network environment. The reinforcement learning model can continuously learn and adapt to these changes, while ensuring effective energy allocation and time coordination, and find the optimal balance between charging and positioning tasks, thereby maximizing network performance and maintaining system stability and efficiency.

[0092] For example, the algorithm starts by initializing the parameters of the deep neural network (DNNs) and j At the beginning of the time slot τ, the algorithm checks whether the remaining energy of the mobile charger (MC) is sufficient to support its return to the base station (BS). If the energy is insufficient, the process will start again. The algorithm collects environmental and state transition information as experience and determines the mobile charger’s next time slot τ. j+1 The next action a j+1 ; Then, based on the calculated new temporal difference error and quantile loss, the DNN parameters are updated, and finally, the action is returned as output, which determines the charging and positioning schedule of the mobile charger.

[0093] According to the embodiments of the present disclosure, the present disclosure has the following technical effects compared with the prior art:

[0094] 1. Improved charging efficiency: This invention uses magnetic resonance coupling technology and beamforming technology to accurately locate sensor nodes, solving the problem of inaccurate GPS positioning, while maximizing charging energy and significantly improving the charging efficiency of wireless rechargeable sensor networks.

[0095] 2. Reduced computational complexity: The present invention proposes a spatiotemporal charging discretization method, which effectively reduces computational complexity and enables rapid determination of suitable charging points while ensuring acceptable performance loss.

[0096] 3. Improved network lifespan: By optimizing charging scheduling paths, charging time slots, and charging points through a trained reinforcement learning model, this invention not only extends the lifespan of the wireless sensor network and reduces network performance degradation due to battery depletion, but also ensures efficient execution of charging tasks and maximizes energy utilization, thereby significantly improving the overall performance and reliability of the network.

[0097] 4. Suitable for multi-scenario applications: The solution of the present invention is not only suitable for monitoring applications in the military, agriculture, forestry and other fields, but also has the potential to be extended to other scenarios that require precise positioning and efficient charging.

[0098] The following describes in detail a wireless charging method 100 for uncertain sensor node locations provided by an embodiment of the present disclosure in conjunction with a specific embodiment, as shown below:

[0099] In this embodiment, a movable wireless charging vehicle equipped with a transmitting coil array composed of multiple coils is specifically taken as an example for description.

[0100] Step 1: The mobile wireless charging vehicle starts to move within the factory area and uses the transmitting coil array to emit low-power detection radio waves.

[0101] When radio waves encounter sensor nodes and obstacles during propagation, they generate reflected signals. The mobile wireless charging cart receives these reflected signals and measures their intensity and phase shift. By analyzing the reflected signals, it can preliminarily identify the approximate distribution areas of each sensor node and obstacle within the two-dimensional space of the factory. For example, if the reflected signal in a certain area exhibits the characteristic frequency and intensity changes of a specific sensor node, it can be preliminarily determined that a sensor node exists in that area. Locations where the signal exhibits obvious reflection, refraction, and absorption characteristics indicate the presence of an obstacle. These characteristics can be used to identify the shape and location of the obstacle. For example, a large metal shelf will produce a specific reflection pattern for the signal, allowing it to be identified.

[0102] Step 2: For each sensor node initially detected, adjust the voltage of each coil in the transmitting coil array individually.

[0103] For example, a known voltage is applied to the first transmitting coil, while the other coils remain open-circuited. The current in the loop is measured, and the total impedance of the receiving coil relative to the transmitting coil is calculated based on the voltage-to-current ratio. The inherent impedance of the circuit is then subtracted to obtain the load impedance, from which the mutual inductance is calculated using the formula. The magnetic channel parameters for the corresponding transmitting coil are calculated using the mutual inductance, and the magnetic beamforming vector for that transmitting coil is generated based on the complex conjugate of the magnetic channel parameters. These steps are repeated for the remaining coils in the transmitting coil array to form multiple magnetic beamforming vectors.

[0104] Based on these magnetic beamforming vectors, the direction from the estimated center of the transmitting coil array to each sensor node is determined, and their common coverage area is found. The center of gravity of this area is used as the precise position of each sensor node to complete the precise calibration of the sensor node position.

[0105] Step 3: Assuming that the length and width of the factory building are 30m and 20m respectively, and setting the side length σ of the grid sub-region to 2m, the entire area is divided into 15×10 grid sub-regions.

[0106] A visibility graph is constructed using mesh vertices to represent sensor nodes and obstacles. If a sensor node exists within a certain mesh sub-region, the sensor node is marked at the corresponding vertex in the visibility graph; if an obstacle exists in the mesh, the vertex is marked as impassable.

[0107] Starting from the starting position of the mobile wireless charging car, a path is planned that can reach each sensor node and avoid obstacles according to the connection relationship between the vertices in the visible graph. The grid vertices on this path constitute the nodes in the complete graph, and the connection relationship of the path corresponds to the edges in the complete graph.

[0108] Step 4: Invoke the traveling salesman problem solver with the goal of minimizing the mobile wireless charging cart's travel costs. Using the locations of each sensor node as city points in the TSP problem, the TSP algorithm calculates the shortest path sequence for the mobile wireless charging cart to visit all sensor nodes. This determines the charging order of each sensor node and generates the initial charging path for the mobile wireless charging cart. For example, the initial charging path might be planned to start from the mobile wireless charging cart's starting position and pass through sensor node 1, sensor node 3, sensor node 2, and so on.

[0109] Step 5: Input the initial charging path into the trained reinforcement learning model. The reinforcement learning model optimizes the initial charging path based on the previously learned sensor node location information, obstacle distribution, state transition information of the mobile wireless charging vehicle, and charging path parameters to generate the optimal charging path.

[0110] The charging task is issued to the mobile wireless charging cart according to the optimal charging path. The mobile wireless charging cart goes to each sensor node location in turn along the path to perform charging operations, ensuring that the sensor node can obtain sufficient energy to maintain normal operation.

[0111] Throughout the implementation process, the reinforcement learning model dynamically adjusts the mobile wireless charging cart's energy distribution during charging tasks and monitors its remaining energy in real time. If the remaining energy falls below a preset threshold, such as less than 20% remaining, the mobile wireless charging cart is controlled to interrupt the charging task and return to the base station for charging, ensuring the device can continue to operate stably and complete the charging task.

[0112] It should be noted that for the aforementioned method embodiments, for simplicity of description, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present disclosure is not limited by the order of the actions described, because according to the present disclosure, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily required by the present disclosure.

[0113] Figure 2A schematic block diagram of an electronic device 200 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0114] The electronic device 200 includes a computing unit 201, which can perform various appropriate actions and processes according to a computer program stored in the ROM 202 or a computer program loaded from the storage unit 208 into the RAM 203. The RAM 203 can also store various programs and data required for the operation of the electronic device 200. The computing unit 201, the ROM 202, and the RAM 203 are connected to each other via a bus 204. An I / O interface 205 is also connected to the bus 204.

[0115] Multiple components in the electronic device 200 are connected to the I / O interface 205, including an input unit 206, such as a keyboard, a mouse, etc.; an output unit 207, such as various types of displays, speakers, etc.; a storage unit 208, such as a magnetic disk, an optical disk, etc.; and a communication unit 209, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 209 allows the electronic device 200 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0116] The computing unit 201 can be a variety of general-purpose and / or specialized processing components with processing and computing capabilities. Some examples of the computing unit 201 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units that run machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The computing unit 201 performs the various methods and processes described above, such as method 100. For example, in some embodiments, method 100 can be implemented as a computer software program that is tangibly contained in a machine-readable medium, such as a storage unit 208. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 200 via ROM 202 and / or communication unit 209. When the computer program is loaded into RAM 203 and executed by the computing unit 201, one or more steps of the method 100 described above can be performed. Alternatively, in other embodiments, the computing unit 201 can be configured to perform method 100 in any other appropriate manner (e.g., by means of firmware).

[0117] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0118] The program code for implementing the method of the present disclosure can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device so that when the program code is executed by the processor or controller, the functions / operations specified in the flow chart and / or block diagram are implemented. The program code can be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0119] In the context of the present disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in conjunction with an instruction execution system, device or equipment. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium can include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0120] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0121] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0122] A computer system may include a client and a server. The client and server are generally remote from each other and typically interact through a communication network. The client-server relationship arises through computer programs running on the respective computers and having a client-server relationship with each other. The server may be a cloud server, a server in a distributed system, or a server integrated with a blockchain.

[0123] It should be understood that the various forms of processes shown above can be used to reorder, add, or delete steps. For example, the steps described in this disclosure can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions of this disclosure can be achieved, and this document is not limited here.

[0124] The above specific embodiments do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure shall be included within the scope of protection of this disclosure.

Claims

1. A wireless charging method without determining the location of a sensor node, characterized in that: include: The transmitting coil array based on the mobile charging device preliminarily detects the distribution of each sensor node and obstacles in the wireless sensor network; determining the precise position of each detected sensor node by individually adjusting the voltage of each coil in the transmitting coil array; Discretize the area where the wireless sensor network is located into N grid sub-areas, construct a visible graph using grid vertices to represent sensor nodes and obstacles, and generate a complete graph of collision-free paths on the visible graph based on the vertex visibility principle; wherein N is a positive integer; Invoking a TSP solver to minimize the movement consumption of the mobile charging device, determine the charging order of the sensor nodes, and generate an initial charging path for the mobile charging device; The initial charging path is input into the trained reinforcement learning model to generate an optimal charging path, and a charging task is issued to the mobile charging device based on the optimal charging path.

2. The method according to claim 1, characterized in that The method further comprises: Based on the trained reinforcement learning model, the energy distribution of the mobile charging device during the charging task is dynamically adjusted, and the remaining energy of the mobile charging device is monitored in real time. If the remaining energy is lower than the preset threshold, the mobile charging device is controlled to interrupt the charging task and return to the base station.

3. The method according to claim 1, characterized in that The training steps of the reinforcement learning model include: The reinforcement learning model is trained based on the position information of each sensor node in the wireless sensor network, the distribution of obstacles, the state transition information of the mobile charging device, and the charging path of the mobile charging device.

4. The method according to claim 1, wherein The step of determining the precise position of each detected sensor node by individually adjusting the voltage of each coil in the transmitting coil array comprises: Forming M magnetic beamforming vectors by individually adjusting the voltage of each coil in the transmitting coil array, wherein M is a positive integer; determining a direction from an estimated center of the transmit coil array to each sensor node based on the M magnetic beamforming vectors; The uncertainty area of ​​each sensor node is determined based on the common coverage area of ​​the M magnetic beamforming vectors, and the center of gravity of the area is used as the precise position of each sensor node.

5. The method according to claim 4, characterized in that The forming of M magnetic beamforming vectors by individually adjusting the voltage of each coil in the transmitting coil array includes: Apply a certain voltage to any coil in the transmitting coil array and measure the corresponding loop current. Calculate the total impedance of the receiving coil relative to the transmitting coil based on the ratio of voltage to current. Calculating the load impedance based on the difference between the total impedance and the inherent impedance of the circuit, and then determining the magnetic channel parameters of the transmitting coil; The transmitting coil magnetic beamforming vector is generated based on the complex conjugate of the magnetic channel parameter, and the above steps are repeated until M magnetic beamforming vectors are formed.

6. The method according to claim 1, characterized in that The obstacle distribution is determined by: By analyzing the reflection, refraction and absorption characteristics of electromagnetic waves on obstacles, the location and shape of obstacles can be identified.

7. The method according to claim 1, characterized in that When the number of sensor nodes in any grid sub-area exceeds a preset threshold, all sensor nodes in the grid sub-area are regarded as virtual nodes, and the node position with the largest receiving power is selected from the virtual nodes as the charging target point.

8. A control method for a mobile wireless charging vehicle, characterized in that: The operation of the mobile wireless charging vehicle is controlled using the optimal charging path generated by the method described in any one of claims 1 to 7.

9. An electronic device comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are configured to cause the computer to execute the method according to any one of claims 1 to 7.

Images