Equipment inspection method and device and electronic equipment

Abstract

The invention provides an equipment inspection method and device and electronic equipment, and belongs to the technical field of inspection. The method comprises the following steps: respectively inputting a plurality of feature vectors obtained by feature extraction of a plurality of candidate radio frequency signals into an equipment distance prediction model to obtain equipment distance information of to-be-detected equipment corresponding to all candidate radio frequency signals output by the equipment distance prediction model; the equipment distance prediction model is constructed based on a time sequence model; determining equipment position information of a target radio frequency signal closest to the current position based on the equipment distance information of all candidate radio frequency signals and the current position of the flight equipment; and calculating flight control data based on the equipment position information of the target radio frequency signal, and controlling the flight equipment to fly to the target to-be-detected equipment sending the target radio frequency signal based on the flight control data for equipment inspection. According to the invention, the problem that there is no suitable path planning algorithm to control the unmanned aerial vehicle to accurately and safely complete the inspection task of the power equipment under the shortest path planning at present is solved.

Description

Technical Field

[0001] The present invention relates to the field of inspection technology, and in particular to an equipment inspection method, an equipment inspection device, an electronic device, a machine-readable storage medium and a computer program product. Background Art

[0002] At present, in the application scenario of power equipment inspection in power grids, in order to improve the inspection efficiency, a method of operating drones to inspect power equipment has emerged. In the inspection mission of power equipment, drones usually have a long distance. At present, there is no more suitable path planning algorithm to control drones to accurately and safely complete the power equipment inspection mission under the shortest distance planning. Summary of the invention

[0003] The purpose of the embodiments of the present invention is to provide an equipment inspection method, an equipment inspection device, an electronic device, a machine-readable storage medium and a computer program product to solve the defect that there is currently no more suitable path planning algorithm to control drones to accurately and safely complete power equipment inspection tasks under the shortest distance planning.

[0004] In order to achieve the above object, an embodiment of the present invention provides an equipment inspection method, which is applied to flight equipment. The method includes:

[0005] Step 100: receiving radio frequency signals sent by a plurality of electronic tags; wherein each of the electronic tags is provided on a single device to be tested;

[0006] Step 200: Based on all the radio frequency signals, the access records of the accessed electronic tags, and the set access time period, determine a plurality of candidate radio frequency signals that have not been accessed from among all the radio frequency signals;

[0007] Step 300: Input multiple feature vectors obtained by feature extraction of the multiple candidate RF signals into a device distance prediction model respectively to obtain device distance information of the device under test corresponding to all candidate RF signals output by the device distance prediction model; the device distance prediction model is constructed based on a time series model;

[0008] Step 400: Based on the device distance information of all candidate RF signals and the current location of the flying device, determine the device location information of the target RF signal closest to the current location;

[0009] Step 500: Calculate flight control data based on the device position information of the target radio frequency signal, and control the flight device to fly to the target device to be tested that sends the target radio frequency signal to perform device inspection based on the flight control data.

[0010] Optionally, the access record of the visited electronic tag includes attribute information and access time of the visited electronic tag, and determining multiple candidate radio frequency signals that have not been visited among all the radio frequency signals based on all the radio frequency signals, the access record of the visited electronic tag, and the set access time period includes:

[0011] Analyzing all the radio frequency signals to obtain attribute information of all the radio frequency signals;

[0012] Based on the attribute information of all radio frequency signals, the attribute information and access time of the visited electronic tags, and the set access time period, a plurality of candidate radio frequency signals that have not been visited among all radio frequency signals are determined.

[0013] Optionally, the determining, based on the attribute information of all radio frequency signals, the attribute information and access time of the visited electronic tags, and the set access time period, a plurality of candidate radio frequency signals that have not been visited among all radio frequency signals includes:

[0014] In the case that the access time of the visited electronic tag is within the set access time period, determining the radio frequency signal having the same attribute information as the visited electronic tag among all radio frequency signals as a repeated access radio frequency signal;

[0015] A plurality of radio frequency signals excluding the repeatedly visited radio frequency signal among all radio frequency signals are determined as a plurality of candidate radio frequency signals that have not been visited.

[0016] Optionally, after determining the device location information of the target radio frequency signal closest to the current location based on the device distance information of all candidate radio frequency signals and the current location of the flying device, the method further includes:

[0017] Execute steps 100 to 400 again to determine the updated device location information of the target radio frequency signal closest to the current location;

[0018] When the updated device location information of the target radio frequency signal is the same as the device location information of the target radio frequency signal, the steps of calculating the flight control data based on the device location information of the target radio frequency signal, and controlling the flight device to fly to the target device to be tested that sends the target radio frequency signal to perform device inspection based on the flight control data are performed;

[0019] When the updated device location information of the target RF signal is different from the device location information of the target RF signal, steps 100 to 400 are performed again to determine the latest device location information of the target RF signal that is closest to the current location.

[0020] Optionally, the device distance information includes the distance and angle between the device to be tested and the flying device; and determining the device position information of the target radio frequency signal closest to the current position based on the device distance information of all candidate radio frequency signals and the current position of the flying device includes:

[0021] Based on the distances of all candidate radio frequency signals, determining the candidate radio frequency signal with the smallest distance as the target radio frequency signal;

[0022] The device position information of the target radio frequency signal is calculated based on the distance and angle between the device under test and the flying device corresponding to the target radio frequency signal and the current position of the flying device.

[0023] Optionally, after calculating flight control data based on the device position information of the target radio frequency signal, and controlling the flight device to fly to the target device to be tested that sends the target radio frequency signal for device inspection based on the flight control data, the method further includes:

[0024] The device location information and inspection completion time of the target device to be tested are stored.

[0025] Optionally, the temporal sequence model uses a long short-term memory network or a gated recurrent unit.

[0026] On the other hand, an embodiment of the present invention further provides an equipment inspection device, comprising:

[0027] A receiving module, used to receive radio frequency signals sent by a plurality of electronic tags; wherein each of the electronic tags is arranged on a single device to be tested;

[0028] A screening module, configured to determine a plurality of candidate radio frequency signals that have not been visited from among all the radio frequency signals based on all the radio frequency signals, the access records of the visited electronic tags, and the set access time period;

[0029] A prediction module, used to input multiple feature vectors obtained by feature extraction of the multiple candidate RF signals into a device distance prediction model respectively, to obtain device distance information of the device to be tested corresponding to all candidate RF signals output by the device distance prediction model; the device distance prediction model is constructed based on a time series model;

[0030] a calculation module, configured to determine the device position information of the target RF signal closest to the current position based on the device distance information of all the candidate RF signals and the current position of the flight device;

[0031] The inspection module is used to calculate flight control data based on the device position information of the target radio frequency signal, and control the flight device to fly to the target device to be tested that sends the target radio frequency signal based on the flight control data to perform device inspection.

[0032] Optionally, the access record of the visited electronic tag includes attribute information and access time of the visited electronic tag, and determining multiple candidate radio frequency signals that have not been visited among all the radio frequency signals based on all the radio frequency signals, the access record of the visited electronic tag, and the set access time period includes:

[0033] Analyzing all the radio frequency signals to obtain attribute information of all the radio frequency signals;

[0034] Based on the attribute information of all radio frequency signals, the attribute information and access time of the visited electronic tags, and the set access time period, a plurality of candidate radio frequency signals that have not been visited among all radio frequency signals are determined.

[0035] Optionally, the determining, based on the attribute information of all radio frequency signals, the attribute information and access time of the visited electronic tags, and the set access time period, a plurality of candidate radio frequency signals that have not been visited among all radio frequency signals includes:

[0036] In the case that the access time of the visited electronic tag is within the set access time period, determining the radio frequency signal having the same attribute information as the visited electronic tag among all radio frequency signals as a repeated access radio frequency signal;

[0037] A plurality of radio frequency signals excluding the repeatedly visited radio frequency signal among all radio frequency signals are determined as a plurality of candidate radio frequency signals that have not been visited.

[0038] Optionally, the device further comprises:

[0039] A first control module, used for controlling the receiving module, the screening module, the prediction module and the calculation module to execute in sequence, so as to determine the update device location information of the target radio frequency signal closest to the current location;

[0040] A second control module, configured to control the inspection module to execute when the update device location information of the target radio frequency signal is the same as the device location information of the target radio frequency signal;

[0041] The third control module is used to control the receiving module, the screening module, the prediction module and the calculation module to execute in sequence to determine the latest device location information of the target radio frequency signal closest to the current position when the updated device location information of the target radio frequency signal is different from the device location information of the target radio frequency signal.

[0042] Optionally, the device distance information includes the distance and angle between the device to be tested and the flying device; and determining the device position information of the target radio frequency signal closest to the current position based on the device distance information of all candidate radio frequency signals and the current position of the flying device includes:

[0043] Based on the distances of all candidate radio frequency signals, determining the candidate radio frequency signal with the smallest distance as the target radio frequency signal;

[0044] The device position information of the target radio frequency signal is calculated based on the distance and angle between the device under test and the flying device corresponding to the target radio frequency signal and the current position of the flying device.

[0045] Optionally, the device further comprises:

[0046] The storage module is used to store the device location information and inspection completion time of the target device to be tested.

[0047] Optionally, the temporal sequence model uses a long short-term memory network or a gated recurrent unit.

[0048] On the other hand, the present invention also 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 implements the above-mentioned device inspection method when executing the program.

[0049] On the other hand, the present invention further provides a machine-readable storage medium having a computer program stored thereon, and the computer program implements the above-mentioned device inspection method when executed by a processor.

[0050] On the other hand, the present invention further provides a computer program product, including a computer program, and when the computer program is executed by a processor, the above-mentioned device inspection method is implemented.

[0051] Through the above technical scheme, the embodiment of the present invention predicts the device distance of the devices to be tested corresponding to multiple candidate RF signals through the device distance prediction model, and then determines the device to be tested corresponding to the target RF signal closest to the current position of the flight device from the multiple candidate RF signals for inspection. The device distance prediction model constructed by the present invention with the help of the time series model can effectively process time series data, capture the characteristics of the time correlation of the signal, and process and predict the RF signal, thereby improving the accuracy of the device distance prediction. The positioning is also performed by receiving the RF signal of the electronic tag on the device to be tested. Since the RF signal of the electronic tag is not affected by environmental factors such as light and weather, it has strong robustness and high security. The embodiment of the present invention enables the flight equipment to automatically and accurately and safely implement the inspection of the equipment under the shortest distance planning.

[0052] Other features and advantages of the embodiments of the present invention will be described in detail in the subsequent detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] The accompanying drawings are used to provide a further understanding of the embodiments of the present invention and constitute a part of the specification. Together with the following specific implementations, they are used to explain the embodiments of the present invention, but do not constitute a limitation on the embodiments of the present invention. In the accompanying drawings:

[0054] Figure 1 This is one of the flow charts of the equipment inspection method provided by the present invention;

[0055] Figure 2 This is the second flow chart of the equipment inspection method provided by the present invention;

[0056] Figure 3 It is a structural schematic diagram of the equipment inspection device provided by the present invention;

[0057] Figure 4 It is one of the structural schematic diagrams of the electronic device provided by the present invention;

[0058] Figure 5 This is the second structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0059] The specific implementation of the embodiment of the present invention is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described here is only used to illustrate and explain the embodiment of the present invention, and is not used to limit the embodiment of the present invention.

[0060] Radio Frequency Identification (RFID) is a contactless automatic identification technology. This technology has been around since the 1990s. It uses radio frequency signals and their spatial coupling transmission characteristics to achieve contactless two-way data communication, thereby using wireless radio frequency to read and write storage media (electronic tags or radio frequency cards) to achieve the purpose of automatic target identification and data exchange.

[0061] A complete RFID system consists of an electronic tag, a reader and a data management system. The RFID system has the ability to be remotely monitored and operated, which liberates the potential of data management and further expands its application areas.

[0062] The basic working principle of radio frequency identification: the electronic tag receives the radio frequency signal of the reader / writer, and uses the energy obtained from the induced current to send out the information data stored in the electronic tag (Passive Tag, passive tag or passive tag), or the electronic tag actively sends information data of a certain frequency (Active Tag, active tag or active tag), and the reader / writer receives it and transmits it to the data management system to process the corresponding data.

[0063] At present, radio frequency identification technology is widely used in logistics management, warehouse management, and identity recognition. Traditional radio frequency identification methods use radio frequency signals to read tag information and simply locate according to signal strength and information transmission time. In the application scenario of power grid inspection, the existing route planning algorithms for drones need to rely on optical sensors. Due to the large number and variety of power equipment, RFID electronic tags are also used in power equipment inspection. In the application scenario of power equipment inspection in power grids, in order to improve the inspection efficiency, methods of operating drones to inspect power equipment have emerged. Drones usually have a long distance in the inspection mission of power equipment. At present, there is no more suitable path planning algorithm to control drones to accurately and safely complete the power equipment inspection mission under the shortest distance planning.

[0064] In view of this, the purpose of the embodiments of the present invention is to provide an equipment inspection method, an equipment inspection device, an electronic device, a machine-readable storage medium and a computer program product to solve the defect that there is currently no more suitable path planning algorithm to control drones to accurately and safely complete power equipment inspection tasks under the shortest distance planning.

[0065] Method Embodiment

[0066] Please refer to Figure 1 The embodiment of the present invention provides an equipment inspection method, which is applied to flight equipment. The method includes:

[0067] Step 100: Receive radio frequency signals sent by multiple electronic tags.

[0068] The equipment inspection method of the present invention is applied to flying equipment, which can be an unmanned aircraft using a radio remote control device and a self-contained program control device, for example, it can include unmanned helicopters, fixed-wing aircraft, multi-rotor aircraft, unmanned airships, unmanned paragliders and other types. The flying equipment of the embodiment of the present invention is described by taking a drone as an example. The equipment to be tested can be various industrial equipment that requires regular inspections, and the embodiment of the present invention is described by taking power equipment in a power grid as an example. Each of the electronic tags is provided on a single power device.

[0069] In the inspection mission of power equipment by drones, inspection route planning plays a very important role. Since there are many types and quantities of power equipment in the inspection, a reasonable inspection route can not only ensure the safety and smooth operation of the drone, but also reduce the time and cost of the inspection, such as saving the power of the drone. In order to complete the inspection mission of various power equipment on the shortest reasonable path, the embodiment of the present invention uses the RFID (Radio Frequency Identification, electronic tag) reader on the drone to receive the radio frequency signal emitted by the RFID electronic tag deployed on the power equipment in the inspection area.

[0070] When a drone enters the signal receiving range of an electronic tag (due to different bands of radio frequency signals, the signal receiving range is different), the drone's onboard RFID reader will send out radio frequency signals within the range. The electronic tags within the range receive the radio frequency signals sent out by the drone's onboard RFID reader, and use the energy obtained from the induced current to send out the information data stored in the electronic tag (Passive Tag, passive tag or passive tag), or the electronic tag actively sends information data of a certain frequency (Active Tag, active tag or active tag). The drone's onboard RFID reader receives radio frequency signals sent out by multiple electronic tags within the range.

[0071] Step 200: Based on all the radio frequency signals, the access records of the accessed electronic tags, and the set access time period, a plurality of candidate radio frequency signals that have not been accessed are determined from among all the radio frequency signals.

[0072] When the drone's onboard RFID reader receives radio frequency signals from multiple RFID tags within range, it records the received radio frequency signals and stores multiple radio frequency signals. The drone's onboard computer decodes and analyzes multiple groups of radio frequency signals, and uses a filtering algorithm to filter out radio frequency signals that have accessed RFID tag information within a time interval based on the recorded access records of the RFID tags.

[0073] For example, the access record of the visited electronic tag includes the attribute information and access time of the visited electronic tag, and the determining of multiple candidate radio frequency signals that have not been visited among all the radio frequency signals based on all the radio frequency signals, the access record of the visited electronic tag, and the set access time period includes:

[0074] Step 210: parse all the radio frequency signals to obtain attribute information of all the radio frequency signals.

[0075] The drone analyzes all the radio frequency signals to obtain attribute information of all the radio frequency signals. The attribute information may be various information representing the uniqueness of the electronic tag, such as the ID code of the electronic tag.

[0076] Step 220: Based on the attribute information of all radio frequency signals, the attribute information and access time of the visited electronic tags, and the set access time period, determine a plurality of candidate radio frequency signals that have not been visited among all radio frequency signals.

[0077] The embodiment of the present invention can preset a set access time period of the electronic tag. For example, 6:00 to 6:30. If the attribute information of all radio frequency signals contains access records of the electronic tag within the set access time period, then the electronic tag belongs to the accessed electronic tag. It is necessary to exclude the radio frequency signal corresponding to the accessed electronic tag from all radio frequency signals, and use the remaining radio frequency signals as multiple candidate radio frequency signals.

[0078] Further, step 220, based on the attribute information of all radio frequency signals, the attribute information and access time of the visited electronic tags, and the set access time period, determining a plurality of candidate radio frequency signals that have not been visited among all radio frequency signals includes:

[0079] Step 221: When the access time of the visited electronic tag is within the set access time period, determine the radio frequency signals having the same attribute information as the visited electronic tag among all radio frequency signals as repeated access radio frequency signals.

[0080] Step 222: Determine multiple radio frequency signals excluding the repeatedly visited radio frequency signal from all radio frequency signals as multiple candidate radio frequency signals that have not been visited.

[0081] For example, the ID code of the visited electronic tag is 1234, and the access time is 6:10. It is currently in the set access time period of 6:00 to 6:30. This means that the power equipment where the electronic tag with ID code 1234 is located has completed an inspection at 6:10. At this time, the power equipment where the electronic tag with ID code 1234 is located does not need to be inspected again. The drone determines the radio frequency signal with the same ID code as the electronic tag with ID code 1234 in all radio frequency signals as a repeated access radio frequency signal, so as to determine multiple radio frequency signals in all radio frequency signals except the repeated access radio frequency signal as multiple candidate radio frequency signals that have not been visited. It should be noted that if the ID codes of all radio frequency signals have recent access records within the set access time period, that is, there is no power equipment (equipped with electronic tags) required to be inspected within this set access time period in the inspection area. If the attribute information of all radio frequency signals only has one radio frequency signal whose ID code has no recent access record within the set access time period, that is, there is only one power equipment (equipped with electronic tags) in the inspection area that is inspected within this set access time period.

[0082] The present invention queries, matches and removes duplicates of the attribute information of the radio frequency signal based on the access records of the accessed electronic tags and the filtering algorithm constructed by setting the access time period. The embodiment of the present invention filters the accessed electronic tag data within the set access time period to avoid repeated inspections and improve the efficiency and accuracy of the inspection task execution.

[0083] Step 300: Input multiple feature vectors obtained by feature extraction of the multiple candidate RF signals into a device distance prediction model respectively to obtain device distance information of the device to be tested corresponding to all candidate RF signals output by the device distance prediction model.

[0084] The drone performs analog-to-digital conversion on each candidate RF signal to obtain a digital signal. Then, the digital signal is subjected to feature extraction of time series features and / or frequency domain features to obtain a feature vector. The feature vectors corresponding to all candidate RF signals are respectively input into the device distance prediction model to obtain the device distance information of the device to be tested corresponding to all candidate RF signals output by the device distance prediction model. The device distance information refers to the distance and angle between the device to be tested and the current position of the drone. Among them, the device distance prediction model is constructed based on the time series model. In the case of classifying and predicting RFID signals using device distance prediction models constructed by algorithms such as support vector machines (SVM) and random forests (RF), these machine learning models have limitations in processing complex time series data and cannot fully utilize the time correlation of RF signals. The embodiment of the present invention constructs a device distance prediction model based on a time series model. Since the time series model can effectively process time series data, capture the time correlation of signals, and fully utilize the correlation of time series data, the accuracy of RF signal processing and electronic tag positioning is improved.

[0085] In some embodiments, the time series model uses a long short-term memory network or a gated recurrent unit. In an embodiment of the present invention, the time series model uses a long short-term memory network. The long short-term memory network includes the following parts:

[0086] 1) Forget Gate: determines which information from the previous moment is discarded.

[0087] f t =σ(W f x t +U f h t-1 +b f ); formula (1)

[0088] Among them, f t is the output of the forget gate, which controls how much past information is forgotten; σ() is the Sigmoid activation function; W f is the weight matrix of the forget gate; b fis the bias term of the forget gate; h t-1 is the hidden state at the previous moment; x t is the input of the current time step; U f is the hidden state weight of the forget gate.

[0089] 2) Input Gate: Determines what new information will be stored in the cell state.

[0090] i t =σ(W i x t +U i h t-1 +b i ); formula (2)

[0091] Among them, i t is the output of the input gate, which controls how much new information is written into the memory cell; W i is the weight matrix of the input gate; b i is the bias term of the input gate; U i is the hidden state weight of the input gate.

[0092] 3) Candidate Cell State: Generate a new candidate cell state.

[0093]

[0094] in, is the candidate memory cell state, generating a new candidate memory; W c is the weight matrix of candidate memory cells; b c is the bias term of the candidate memory cell; U c is the hidden state weight of the candidate memory cell.

[0095] 4) Cell State: Updates the cell state.

[0096]

[0097] Among them, C t is the memory cell state at the current time step; C t-1 is the cell state at the previous moment.

[0098] 5) Output Gate: determines the output content.

[0099] o t =σ(W o x t +U o h t-1 +b o); formula (5)

[0100] Among them, t is the output of the output gate, which controls how the state of the memory cell affects the hidden state of the current time step; W o is the weight matrix of the output gate; b o is the bias term of the output gate; U o is the hidden state weight of the output gate.

[0101] 6) Hidden State: Generates the hidden state at the current moment.

[0102] h t =o t ☉tanh(c t ). Formula (6)

[0103] Among them, h t is the hidden state at the current time step.

[0104] In one embodiment, the device distance prediction model is trained by the following steps:

[0105] Step 10: Acquire multiple radio frequency sample signals within a set historical period;

[0106] Repeat the following steps until the set number of times is reached:

[0107] Step 20: inputting a first RF sample signal into the device distance prediction model to obtain a model output value of the device distance prediction model; the first RF sample signal is any one of a plurality of RF sample signals;

[0108] Step 30: Calculate a loss function based on the model output value and the label value of the first RF sample signal;

[0109] Step 40: Adjust model parameters of the device distance prediction model based on the loss function.

[0110] First, the drone collects RF sample signals, for example, using the RFID reader on the drone to collect the RF signal of the electronic tag sent by the power equipment to generate time series data. For example, by collecting the RF signal of the electronic tag sent by the power equipment in the past hour, multiple RF sample signals collected in one hour are obtained, and there is time correlation between the multiple RF sample signals. Each RF sample signal is input into the long short-term memory network. The long short-term memory network can learn signal characteristics and time correlation, and the long short-term memory network outputs the distance and angle of the power equipment from the drone corresponding to the RF sample signal. The drone calculates the loss function based on the distance and angle output by the model, as well as the actual distance and actual angle of the power equipment from the drone corresponding to the RF sample signal. According to the value of the loss function, the back propagation algorithm is used to calculate the gradient of each weight and bias in the long short-term memory network. Then, the gradient descent method or other optimization algorithms are used to update the weights and biases in the long short-term memory network. After multiple iterative training processes, a trained long short-term memory network is obtained. In order to use the trained long short-term memory network to process the RF signal of the real-time electronic tag, predict the location of each electronic tag, and find the nearest electronic tag.

[0111] Compared with the device distance prediction model constructed using machine learning models such as support vector machines and random forests, the device distance prediction model constructed based on the long short-term memory network in the embodiment of the present invention has higher positioning accuracy. The long short-term memory network can effectively process time series data, capture the time correlation of signals, and improve the accuracy of electronic tag positioning. Secondly, the long short-term memory network has stronger adaptability. The device distance prediction model constructed based on the long short-term memory network can adapt to different environments and signal scenarios, especially in complex environments with severe multi-path interference and signal attenuation, and has stronger robustness. Finally, the long short-term memory network has high data utilization efficiency. The device distance prediction model constructed based on the long short-term memory network can make full use of historical information when processing time series data, so that a large amount of labeled data training is not required, which reduces the cost of data acquisition.

[0112] Step 400: Based on the device distance information of all the candidate radio frequency signals and the current position of the flying device, determine the device position information of the target radio frequency signal closest to the current position.

[0113] The device distance information includes the distance and angle between the power device (or electronic tag) and the drone. The drone of the embodiment of the present invention can determine the device location information of the target RF signal closest to the current location based on the distance and angle between all candidate RF signals and the flying device and the current location of the flying device.

[0114] Specifically, step 400, based on the device distance information of all candidate radio frequency signals and the current location of the flying device, determining the device location information of the target radio frequency signal closest to the current location, includes:

[0115] Step 410: Based on the distances of all candidate RF signals, determine the candidate RF signal with the shortest distance as the target RF signal.

[0116] Step 420: Calculate device location information of the target RF signal based on the distance and angle between the device under test and the flying device corresponding to the target RF signal and the current location of the flying device.

[0117] By predicting multiple candidate RF signals through the device distance prediction model, the distance and angle between the power equipment and the drone corresponding to each candidate RF signal can be obtained. From multiple distances, the candidate RF signal corresponding to the first distance can be determined as the target RF signal. The drone then calculates the device location information of the target RF signal based on the distance and angle between the power equipment corresponding to the target RF signal and the drone and the current location of the drone.

[0118] The distance calculation formula of the drone is as follows:

[0119]

[0120] In the above formula, d is the distance between the power equipment and the drone corresponding to the target RF signal, and x target ,y target , z target is the three-dimensional coordinate of the power equipment location corresponding to the target RF signal, x current ,y current , z current is the three-dimensional coordinate of the current position of the drone.

[0121] In UAV flight control, the calculation formula for the rotation parameters of the UAV around the vertical axis is as follows:

[0122] ψ=arctan2(y target -y current , x target -x current ); formula (8)

[0123] In the above formula, the parameter ψ controls the rotation of the drone around the vertical axis and can be adjusted according to the horizontal direction and distance of the power equipment corresponding to the target RF signal.

[0124] In UAV flight control, the calculation formula for the forward or backward tilt parameters of the UAV is as follows:

[0125] θ=kθ (x target -x current ;Formula (9)

[0126] In the above formula, the parameter θ controls the forward or backward tilt of the drone, which can be adjusted according to the front and rear distance of the power device corresponding to the target RF signal. k6 is the proportional gain constant.

[0127] In UAV flight control, the calculation formula for the tilt parameter of the left or right side of the UAV is as follows:

[0128] φ=k φ (y target -y current ;Formula (10)

[0129] In the above formula, the parameter φ controls the tilt of the UAV to the left or right, which can be adjusted according to the distance between the left and right sides of the power equipment corresponding to the target RF signal. φ is the proportional gain constant.

[0130] In drone flight control, the calculation formula for the drone flight angle is as follows:

[0131] A=function of (θ, φ, ψ); formula (11)

[0132] In the above formula, parameter A controls the automatic adjustment of the drone angle.

[0133] When the distance and angle between the power equipment corresponding to the target RF signal and the UAV and the current position of the UAV are obtained, the device position information of the target RF signal can be calculated by solving the above formulas.

[0134] Step 500: Calculate flight control data based on the device position information of the target radio frequency signal, and control the flight device to fly to the target device to be tested that sends the target radio frequency signal to perform device inspection based on the flight control data.

[0135] In drone flight control, the calculation formula for drone hovering is as follows:

[0136]

[0137] In the above formula, the parameter H controls the hovering of the UAV and can be judged and adjusted according to the distance threshold of the power equipment corresponding to the target RF signal.

[0138] In UAV flight control, the calculation formula of the UAV's flight altitude is as follows:

[0139] T=k T (z target -zcurrent ); formula (13)

[0140] In the above formula, the parameter T controls the flight altitude of the UAV and can be adjusted according to the vertical distance of the power equipment location corresponding to the target RF signal. T is the proportional gain constant.

[0141] Based on the device location information of the target RF signal, the drone can calculate the hovering, flight altitude, flight distance and flight angle of the drone through the drone flight control algorithm (or control module) of formula (7) to formula (13), so as to control the flight device to fly to the target device to be tested that sends the target RF signal for equipment inspection based on the above flight control data.

[0142] In one embodiment, the pseudo code for calculating the hovering, flight altitude, flight distance and flight angle of the drone is as follows:

[0143] 1. Initialization:

[0144] -Define constants k_T,k_θ, threshold

[0145] 2.Calculate Control Parameters:

[0146] -Input:Current UAV position(x_current,y_current,z_current),Targetposition(x_target,y_target,z_target)

[0147] -Output:Control parameters(Throttle,Yaw,Pitch,Roll,Hover,Angle / Auto)

[0148] function Calculate_Control_Parameters(x_current,y_current,z_current,x_target,y_target,z_target): / / Calculate the flight distance of the drone

[0149] T = k_T * (z_target-z_current) / / Calculate the flight altitude of the drone

[0150] ψ=arctan2(y_target-y_current,x_target-x_current) / / Calculate the rotation parameters of the drone around the vertical axis

[0151] θ=k_θ*(x_target-x_current) / / Calculate the forward or backward tilt parameters of the drone / / Calculate the tilt parameters of the left or right side of the drone

[0152] distance=sqrt((x_target-x_current)^2+(y_target-y_current)^2+(z_target-z_current)^2)

[0153] if distance <threshold:

[0154] H=1

[0155] else:

[0156] H=0 / / Calculate the hovering of the drone

[0157] / / Calculate the flight angle of the drone

[0158] return

[0159] 3.Control UAV:

[0160] -Input:Control parameters

[0161] -Output:Adjust UAV flight path

[0162] function Control_UAV

[0163] if H == 1:

[0164] Maintain current position

[0165] else:

[0166] Adjust Throttle to T

[0167] Adjust Yaw toψ

[0168] Adjust Pitch toθ

[0169] Adjust Roll to

[0170] Adjust Angle / Auto to A

[0171] 4.Main Loop:

[0172] -Continuously update UAV position and calculate control parameters

[0173] while True:

[0174] (x_current,y_current,z_current)=Get_UAV_Position()

[0175] (x_target,y_target,z_target)=Get_Target_Position()

[0176]

[0177] Control_UAV

[0178] Please refer to Figure 2 In summary, after the onboard processor of the drone analyzes the radio frequency signals emitted by the electronic tags in the inspection area, it uses a filtering algorithm to filter the electronic tags that have been visited within the specified time interval, and then uses the long short-term memory network and electronic tag fusion algorithm (LSTM-RFID algorithm) to determine the location of the power equipment corresponding to the target radio frequency signal that requires inspection in the area, calculate the shortest inspection path, and then use the drone flight control algorithm to calculate the flight control data of the drone. Finally, the onboard processor of the drone transmits the flight control data of the drone to the control module (or flight control module) to control the drone to automatically complete the inspection task of the RFID electronic tag power equipment deployed in the area on the shortest path.

[0179] The embodiment of the present invention predicts the device distance of the devices to be tested corresponding to multiple candidate RF signals through a device distance prediction model, and then determines the device to be tested corresponding to the target RF signal closest to the current position of the flying device from the multiple candidate RF signals for inspection. The device distance prediction model constructed by the present invention with the help of the time series model can effectively process time series data, capture the characteristics of the time correlation of the signal, and process and predict the RF signal, thereby improving the accuracy of the device distance prediction. The positioning is also performed by receiving the RF signal of the electronic tag on the device to be tested. Since the RF signal of the electronic tag is not affected by environmental factors such as light and weather, it has strong robustness and high security. The embodiment of the present invention enables the flying equipment to automatically and accurately and safely implement the inspection of the equipment under the shortest distance planning.

[0180] In other aspects of the embodiments of the present invention, after step 400, based on the device distance information of all candidate RF signals and the current location of the flying device, determining the device location information of the target RF signal closest to the current location, further includes:

[0181] Execute steps 100 to 400 again to determine the updated device location information of the target radio frequency signal closest to the current location;

[0182] When the updated device location information of the target radio frequency signal is the same as the device location information of the target radio frequency signal, the steps of calculating the flight control data based on the device location information of the target radio frequency signal, and controlling the flight device to fly to the target device to be tested that sends the target radio frequency signal to perform device inspection based on the flight control data are performed;

[0183] When the updated device location information of the target RF signal is different from the device location information of the target RF signal, steps 100 to 400 are performed again to determine the latest device location information of the target RF signal that is closest to the current location.

[0184] Since the drone may move, the device location information of the target RF signal closest to the current location may change after the movement. In order to recalculate and verify the device location information of the target RF signal closest to the current location. In this embodiment of the present invention, after step 400, steps 100 to 400 are executed again to determine the updated device location information of the target RF signal closest to the current location. By comparing the device location information calculated twice, if they are the same, it means that the device location information calculated last time is correct, then step 500 is executed, and the step of calculating the flight control data based on the device location information of the target RF signal is executed, and the flight device is controlled to fly to the target device to be tested that sends the target RF signal to perform equipment inspection based on the flight control data. If they are not the same, steps 100 to 400 are executed again to determine the latest device location information of the target RF signal closest to the current location. The flight control data is calculated based on the device location information of the latest calculated target RF signal for inspection.

[0185] The embodiment of the present invention confirms whether the closest RF signals among multiple groups of RF signals are consistent by repeatedly executing steps 100 to 400, thereby performing secondary verification of the device location information of the target RF signal closest to the current location, thereby improving the accuracy of the inspection task execution.

[0186] In other aspects of the embodiments of the present invention, after step 500, calculating flight control data based on the device position information of the target radio frequency signal, and controlling the flight device to fly to the target device under test that sends the target radio frequency signal for device inspection based on the flight control data, it also includes: step 600, storing the device position information of the target device under test and the inspection completion time.

[0187] The drone completes the inspection task of the nearest power equipment (equipped with electronic tags), records the device location information, attribute information, access time and other information data of the electronic tags, and searches for the next power equipment (equipped with electronic tags) to complete the inspection task. The drone stores the device location information, attribute information and access time and other information data of the electronic tags that have been visited, and returns the information that "the inspection of RFID power equipment in this area is completed". Then it goes to the next area for inspection. By storing the device location information and inspection completion time of the target device to be tested, the power equipment corresponding to the electronic tags that have been visited can be recorded to avoid multiple inspections of the same power equipment within the set access time period, thereby improving the efficiency and accuracy of the inspection task execution.

[0188] In summary, drones are currently used to complete some power inspection tasks. In the inspection of electronic tag-deployed power equipment and the control of drones, radio frequency signals and deep learning algorithms have not yet been used to plan the inspection routes of drones. Compared with the method of manually controlling drone inspections, the method adopted in the embodiment of the present invention is relatively low-cost and allows drones to automatically complete the inspection tasks of electronic tag-deployed power equipment in the area. The radio frequency signal of the electronic tag in the embodiment of the present invention is not affected by environmental factors such as light and weather, and is highly robust, safe, effective, and accurate in recognition.

[0189] Although there are methods for processing RF signals using machine learning methods, they are limited in processing complex time series data and cannot fully utilize the temporal correlation of RF signals. In addition, these methods usually require a large amount of labeled data for training, which has high data collection costs. In addition, the models are easily affected by environmental changes in actual applications, resulting in reduced accuracy.

[0190] The present invention improves the RF signal processing capability and the positioning accuracy of electronic tags, especially in complex environments, by utilizing the correlation of time series data and performing RF signal processing and prediction through a time series model. This enables accurate path planning and control of drones, and improves the efficiency and accuracy of inspection mission execution. Compared with existing technical solutions using machine learning algorithms such as SVM and RF, the present invention has the following technical advantages:

[0191] 1) Higher positioning accuracy: Long short-term memory networks can effectively process time series data, capture the temporal correlation of signals, and improve the positioning accuracy of electronic tags, especially in complex environments with severe multipath interference and signal attenuation.

[0192] 2) Stronger adaptability: The model based on long short-term memory network can adapt to different environments and signal scenarios and has stronger robustness.

[0193] 3) High data utilization efficiency: When processing time series data, the long short-term memory network can make full use of historical information, thus eliminating the need for a large amount of labeled data training and reducing data collection costs.

[0194] 4) Efficient path planning: Through accurate electronic tag positioning information, efficient path planning and control of drones can be achieved, improving the efficiency and accuracy of inspection tasks.

[0195] Device Embodiment

[0196] Please refer to Figure 3 On the other hand, an embodiment of the present invention further provides an equipment inspection device, comprising:

[0197] The receiving module 301 is used to receive radio frequency signals sent by multiple electronic tags; each of the electronic tags is provided on a single device to be tested;

[0198] A screening module 302, configured to determine a plurality of candidate radio frequency signals that have not been visited from among all the radio frequency signals based on all the radio frequency signals, the access records of the visited electronic tags, and the set access time period;

[0199] The prediction module 303 is used to input the multiple feature vectors obtained by feature extraction of the multiple candidate RF signals into the device distance prediction model respectively, and obtain the device distance information of the device to be tested corresponding to all the candidate RF signals output by the device distance prediction model; the device distance prediction model is constructed based on the time series model;

[0200] A calculation module 304 is used to determine the device position information of the target RF signal closest to the current position based on the device distance information of all candidate RF signals and the current position of the flying device;

[0201] The inspection module 305 is used to calculate flight control data based on the device position information of the target RF signal, and control the flight device to fly to the target device to be tested that sends the target RF signal based on the flight control data to perform device inspection.

[0202] Optionally, the access record of the visited electronic tag includes attribute information and access time of the visited electronic tag, and determining multiple candidate radio frequency signals that have not been visited among all the radio frequency signals based on all the radio frequency signals, the access record of the visited electronic tag, and the set access time period includes:

[0203] Analyzing all the radio frequency signals to obtain attribute information of all the radio frequency signals;

[0204] Based on the attribute information of all radio frequency signals, the attribute information and access time of the visited electronic tags, and the set access time period, a plurality of candidate radio frequency signals that have not been visited among all radio frequency signals are determined.

[0205] Optionally, the determining, based on the attribute information of all radio frequency signals, the attribute information and access time of the visited electronic tags, and the set access time period, a plurality of candidate radio frequency signals that have not been visited among all radio frequency signals includes:

[0206] In the case that the access time of the visited electronic tag is within the set access time period, determining the radio frequency signal having the same attribute information as the visited electronic tag among all radio frequency signals as a repeated access radio frequency signal;

[0207] A plurality of radio frequency signals excluding the repeatedly visited radio frequency signal among all radio frequency signals are determined as a plurality of candidate radio frequency signals that have not been visited.

[0208] Optionally, the device further comprises:

[0209] A first control module, used for controlling the receiving module, the screening module, the prediction module and the calculation module to execute in sequence, so as to determine the update device location information of the target radio frequency signal closest to the current location;

[0210] A second control module, configured to control the inspection module to execute when the update device location information of the target radio frequency signal is the same as the device location information of the target radio frequency signal;

[0211] The third control module is used to control the receiving module, the screening module, the prediction module and the calculation module to execute in sequence to determine the latest device location information of the target radio frequency signal closest to the current position when the updated device location information of the target radio frequency signal is different from the device location information of the target radio frequency signal.

[0212] Optionally, the device distance information includes the distance and angle between the device to be tested and the flying device; and determining the device position information of the target radio frequency signal closest to the current position based on the device distance information of all candidate radio frequency signals and the current position of the flying device includes:

[0213] Based on the distances of all candidate radio frequency signals, determining the candidate radio frequency signal with the smallest distance as the target radio frequency signal;

[0214] The device position information of the target radio frequency signal is calculated based on the distance and angle between the device under test and the flying device corresponding to the target radio frequency signal and the current position of the flying device.

[0215] Optionally, the device further comprises:

[0216] The storage module is used to store the device location information and inspection completion time of the target device to be tested.

[0217] Optionally, the temporal sequence model uses a long short-term memory network or a gated recurrent unit.

[0218] The equipment inspection device includes a processor and a memory. The above-mentioned receiving module 301, screening module 302, prediction module 303, calculation module 304 and inspection module 305 are all stored in the memory as program units, and the processor executes the above-mentioned program units stored in the memory to realize corresponding functions.

[0219] The processor includes a kernel, which calls the corresponding program unit from the memory. There can be one or more kernels.

[0220] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0221] Figure 4 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 4 As shown, the electronic device may include: a processor (processor) 410, a communication interface (Communications Interface) 420, a memory (memory) 430 and a communication bus 440, wherein the processor 410, the communication interface 420, and the memory 430 communicate with each other through the communication bus 440. The processor 410 can call the logic instructions in the memory 430 to execute the equipment inspection method, which includes: step 100, receiving radio frequency signals sent by multiple electronic tags; wherein each of the electronic tags is set on a single device to be tested; step 200, based on all the radio frequency signals, the access records of the accessed electronic tags and the set access time period, determining multiple candidate radio frequency signals that have not been visited among all the radio frequency signals; step 300, inputting multiple feature vectors obtained by feature extraction of the multiple candidate radio frequency signals into the equipment distance prediction model respectively, and obtaining the equipment distance information of all the candidate radio frequency signals output by the equipment distance prediction model corresponding to the device to be tested; the equipment distance prediction model is constructed based on the time series model; step 400, based on the equipment distance information of all the candidate radio frequency signals and the current position of the flying device, determining the equipment position information of the target radio frequency signal closest to the current position; step 500, calculating flight control data based on the equipment position information of the target radio frequency signal, and controlling the flying device to fly to the target device to be tested that sends the target radio frequency signal based on the flight control data to perform equipment inspection.

[0222] In addition, the logic instructions in the above-mentioned memory 430 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0223] Please refer to Figure 5 The electronic device of the embodiment of the present invention may be a drone. After the drone analyzes the radio frequency signal emitted by the electronic tag in the inspection area through the onboard processor, the drone uses the filtering algorithm to filter the electronic tags that have been visited within the specified time interval, and then uses the algorithm of long short-term memory network and electronic tag fusion (LSTM-RFID algorithm) to determine the location of the power equipment corresponding to the target radio frequency signal required for inspection in the area, calculate the shortest inspection path, and then use the drone flight control algorithm to calculate the flight control data of the drone. Finally, the drone onboard processor transmits the flight control data of the drone to the control module to control the drone to automatically complete the inspection task of the RFID electronic tag power equipment deployed in the area on the shortest path.

[0224] On the other hand, the present invention also provides a computer program product, the computer program product includes a computer program, the computer program can be stored on a machine-readable storage medium, when the computer program is executed by a processor, the computer can execute a device inspection method, the method comprising: step 100, receiving radio frequency signals sent by multiple electronic tags; wherein each of the electronic tags is set on a single device to be tested; step 200, based on all the radio frequency signals, access records of the accessed electronic tags and a set access time period, determining multiple candidate radio frequency signals that have not been visited in all the radio frequency signals; step 300, inputting multiple feature vectors obtained by feature extraction of the multiple candidate radio frequency signals into a device distance prediction model respectively, to obtain device distance information of all candidate radio frequency signals corresponding to the device to be tested output by the device distance prediction model; the device distance prediction model is constructed based on a time series model; step 400, based on the device distance information of all candidate radio frequency signals and the current position of the flying device, determining the device position information of the target radio frequency signal closest to the current position; step 500, calculating flight control data based on the device position information of the target radio frequency signal, and controlling the flying device to fly to the target device to be tested that sends the target radio frequency signal based on the flight control data to perform equipment inspection.

[0225] On the other hand, the present invention also provides a machine-readable storage medium having a computer program stored thereon, which is implemented when executed by a processor to perform a device inspection method, the method comprising: step 100, receiving radio frequency signals sent by multiple electronic tags; wherein each of the electronic tags is set on a single device to be tested; step 200, based on all the radio frequency signals, access records of accessed electronic tags, and a set access time period, determining multiple candidate radio frequency signals that have not been accessed among all the radio frequency signals; step 300, inputting multiple feature vectors obtained by feature extraction of the multiple candidate radio frequency signals into a device distance prediction model respectively, to obtain device distance information of all candidate radio frequency signals corresponding to the device to be tested output by the device distance prediction model; the device distance prediction model is constructed based on a time series model; step 400, based on the device distance information of all candidate radio frequency signals and the current position of the flying device, determining the device position information of the target radio frequency signal closest to the current position; step 500, calculating flight control data based on the device position information of the target radio frequency signal, and controlling the flying device to fly to the target device to be tested that sends the target radio frequency signal based on the flight control data to perform device inspection.

[0226] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0227] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0228] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A device inspection method, characterized in that: Applied to flight equipment, the method comprises: Step 100: receiving radio frequency signals sent by a plurality of electronic tags; wherein each of the electronic tags is provided on a single device to be tested; Step 200: Based on all the radio frequency signals, the access records of the accessed electronic tags, and the set access time period, determine a plurality of candidate radio frequency signals that have not been accessed from among all the radio frequency signals; Step 300: Input multiple feature vectors obtained by feature extraction of the multiple candidate RF signals into a device distance prediction model respectively to obtain device distance information of the device under test corresponding to all candidate RF signals output by the device distance prediction model; the device distance prediction model is constructed based on a time series model; Step 400: Based on the device distance information of all candidate RF signals and the current location of the flying device, determine the device location information of the target RF signal closest to the current location; Step 500: Calculate flight control data based on the device position information of the target radio frequency signal, and control the flight device to fly to the target device to be tested that sends the target radio frequency signal to perform device inspection based on the flight control data.

2. The equipment inspection method according to claim 1, characterized in that: After determining the device location information of the target radio frequency signal closest to the current location based on the device distance information of all candidate radio frequency signals and the current location of the flying device, the method further includes: Execute steps 100 to 400 again to determine the updated device location information of the target radio frequency signal closest to the current location; When the updated device location information of the target radio frequency signal is the same as the device location information of the target radio frequency signal, the steps of calculating the flight control data based on the device location information of the target radio frequency signal, and controlling the flight device to fly to the target device to be tested that sends the target radio frequency signal to perform device inspection based on the flight control data are performed; When the updated device location information of the target RF signal is different from the device location information of the target RF signal, steps 100 to 400 are performed again to determine the latest device location information of the target RF signal that is closest to the current location.

3. The equipment inspection method according to claim 1, characterized in that: After calculating the flight control data based on the device position information of the target radio frequency signal, and controlling the flight device to fly to the target device to be tested that sends the target radio frequency signal to perform device inspection based on the flight control data, the method further includes: The device location information and inspection completion time of the target device to be tested are stored.

4. The equipment inspection method according to claim 1, characterized in that: The access record of the visited electronic tag includes attribute information and access time of the visited electronic tag, and the determining of multiple candidate radio frequency signals that have not been visited among all the radio frequency signals based on all the radio frequency signals, the access record of the visited electronic tag, and the set access time period includes: Analyzing all the radio frequency signals to obtain attribute information of all the radio frequency signals; Based on the attribute information of all radio frequency signals, the attribute information and access time of the visited electronic tags, and the set access time period, a plurality of candidate radio frequency signals that have not been visited among all radio frequency signals are determined.

5. The equipment inspection method according to claim 4, characterized in that: The determining of a plurality of candidate radio frequency signals that have not been visited among all radio frequency signals based on the attribute information of all radio frequency signals, the attribute information and the access time of the visited electronic tags, and the set access time period includes: In the case that the access time of the visited electronic tag is within the set access time period, determining the radio frequency signal having the same attribute information as the visited electronic tag among all radio frequency signals as a repeated access radio frequency signal; A plurality of radio frequency signals excluding the repeatedly visited radio frequency signal among all radio frequency signals are determined as a plurality of candidate radio frequency signals that have not been visited.

6. The equipment inspection method according to claim 1, characterized in that: The device distance information includes the distance and angle between the device to be tested and the flying device; the device position information of the target radio frequency signal closest to the current position is determined based on the device distance information of all candidate radio frequency signals and the current position of the flying device, including: Based on the distances of all candidate radio frequency signals, determining the candidate radio frequency signal with the smallest distance as the target radio frequency signal; The device position information of the target radio frequency signal is calculated based on the distance and angle between the device under test and the flying device corresponding to the target radio frequency signal and the current position of the flying device.

7. The equipment inspection method according to claim 1, characterized in that: The temporal sequence model uses a long short-term memory network or a gated recurrent unit.

8. An equipment inspection device, characterized in that: include: A receiving module, used for receiving radio frequency signals sent by multiple electronic tags; Each of the electronic tags is arranged on a single device to be tested; A screening module, configured to determine a plurality of candidate radio frequency signals that have not been visited from among all the radio frequency signals based on all the radio frequency signals, the access records of the visited electronic tags, and the set access time period; A prediction module, used to input multiple feature vectors obtained by feature extraction of the multiple candidate RF signals into a device distance prediction model respectively, to obtain device distance information of the device to be tested corresponding to all candidate RF signals output by the device distance prediction model; the device distance prediction model is constructed based on a time series model; a calculation module, configured to determine the device position information of the target RF signal closest to the current position based on the device distance information of all the candidate RF signals and the current position of the flight device; The inspection module is used to calculate flight control data based on the device position information of the target radio frequency signal, and control the flight device to fly to the target device to be tested that sends the target radio frequency signal based on the flight control data to perform device inspection.

9. The equipment inspection device according to claim 8, characterized in that: The device also includes: A first control module, used for controlling the receiving module, the screening module, the prediction module and the calculation module to execute in sequence, so as to determine the update device location information of the target radio frequency signal closest to the current location; A second control module, configured to control the inspection module to execute when the update device location information of the target radio frequency signal is the same as the device location information of the target radio frequency signal; The third control module is used to control the receiving module, the screening module, the prediction module and the calculation module to execute in sequence to determine the latest device location information of the target radio frequency signal closest to the current position when the updated device location information of the target radio frequency signal is different from the device location information of the target radio frequency signal.

10. The equipment inspection device according to claim 8, characterized in that: The device also includes: The storage module is used to store the device location information and inspection completion time of the target device to be tested.

11. The equipment inspection device according to claim 8, characterized in that: The access record of the visited electronic tag includes attribute information and access time of the visited electronic tag, and the determining of multiple candidate radio frequency signals that have not been visited among all the radio frequency signals based on all the radio frequency signals, the access record of the visited electronic tag, and the set access time period includes: Analyzing all the radio frequency signals to obtain attribute information of all the radio frequency signals; Based on the attribute information of all radio frequency signals, the attribute information and access time of the visited electronic tags, and the set access time period, a plurality of candidate radio frequency signals that have not been visited among all radio frequency signals are determined.

12. The equipment inspection device according to claim 11, characterized in that: The determining of a plurality of candidate radio frequency signals that have not been visited among all radio frequency signals based on the attribute information of all radio frequency signals, the attribute information and the access time of the visited electronic tags, and the set access time period includes: In the case that the access time of the visited electronic tag is within the set access time period, determining the radio frequency signal having the same attribute information as the visited electronic tag among all radio frequency signals as a repeated access radio frequency signal; A plurality of radio frequency signals excluding the repeatedly visited radio frequency signal among all radio frequency signals are determined as a plurality of candidate radio frequency signals that have not been visited.

13. The equipment inspection device according to claim 8, characterized in that: The device distance information includes the distance and angle between the device to be tested and the flying device; the device position information of the target radio frequency signal closest to the current position is determined based on the device distance information of all candidate radio frequency signals and the current position of the flying device, including: Based on the distances of all candidate radio frequency signals, determining the candidate radio frequency signal with the smallest distance as the target radio frequency signal; The device position information of the target radio frequency signal is calculated based on the distance and angle between the device under test and the flying device corresponding to the target radio frequency signal and the current position of the flying device.

14. The equipment inspection device according to claim 8, characterized in that: The temporal sequence model uses a long short-term memory network or a gated recurrent unit.

15. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the device inspection method according to any one of claims 1 to 7 is implemented.

16. A machine-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the device inspection method according to any one of claims 1 to 7 is implemented.

17. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the device inspection method according to any one of claims 1 to 7 is implemented.

Images