UWB-based power plant personnel real-time positioning method and device

Abstract

The invention discloses a UWB-based power plant personnel real-time positioning method and device, and relates to the technical field of positioning, and the method comprises the steps: obtaining the original ranging data of a target person through the communication data of a UWB base station network and a positioning tag; based on a personnel positioning model, calculating according to the original ranging data to obtain an initial three-dimensional coordinate; performing residual compensation on the initial three-dimensional coordinates through a convolutional neural network to obtain corrected high-precision position coordinates; and mapping the high-precision position coordinates to a three-dimensional visual model, dynamically rendering the target person and the environment scene, and determining the real-time position of the target person. By means of the mode, the technical problems that in the prior art, the positions of the power plant personnel cannot be accurately positioned, and the activity area of the power plant personnel cannot be monitored are solved.

Description

Technical Field

[0001] This application relates to the field of positioning technology, and particularly to a real-time positioning method and device for power plant personnel based on UWB. Background Art

[0002] Traditional power plant personnel positioning systems mainly rely on RFID or Bluetooth technology, which have obvious deficiencies in positioning accuracy and anti-interference ability. The positioning accuracy of RFID technology is usually between 3 and 5 meters, and that of Bluetooth technology is also roughly the same. Both are vulnerable to interference from other wireless signals in the environment, resulting in inaccurate positioning. In addition, the existing systems lack the ability to analyze and predict personnel behavior and cannot effectively prevent personnel from entering dangerous areas. The current two-dimensional positioning systems are difficult to accurately reflect the spatial characteristics in complex industrial environments, cannot accurately and real-time locate the positions of various types of personnel in the power plant, and cannot timely sense whether power plant workers enter dangerous areas.

[0003] The above content is only used to assist in understanding the technical solution of the present invention and does not represent an admission that the above content is prior art. Summary of the Invention

[0004] The main purpose of this application is to provide a real-time positioning method and device for power plant personnel based on UWB, aiming to solve the technical problems in the prior art that the location of power plant personnel cannot be accurately positioned and the activity areas of power plant personnel cannot be monitored.

[0005] To achieve the above purpose, this application provides a real-time positioning method for power plant personnel based on UWB, and the method includes:

[0006] Obtaining the original ranging data of the target personnel through the communication data between the UWB base station network and the positioning tag;

[0007] Based on the personnel positioning model, calculating the initial three-dimensional coordinates according to the original ranging data;

[0008] Performing residual compensation on the initial three-dimensional coordinates through a convolutional neural network to obtain the corrected high-precision position coordinates;

[0009] Mapping the high-precision position coordinates to a three-dimensional visualization model, dynamically rendering the target personnel and the environmental scene, and determining the real-time position of the target personnel.

[0010] In an embodiment, the step of obtaining the original ranging data of the target personnel through the communication data between the UWB base station network and the positioning tag includes:

[0011] When the positioning signal of the positioning tag is detected in the UWB base station network, recording the positioning signal;

[0012] When the positioning signal is within the detection range of the UWB base station network, the real-time distance between the positioning signal and the UWB base station can be determined at a preset detection period;

[0013] Map the positioning signal and the real-time distance to the local coordinate system corresponding to the UWB base station, and determine the local coordinate position of the positioning signal in the local coordinate system;

[0014] Sort the local coordinate positions based on the timestamp sequence of the detection period to generate original ranging data.

[0015] In one embodiment, the step of calculating the initial three-dimensional coordinates according to the original ranging data based on the personnel positioning model includes:

[0016] Determine the positioning area of the target person according to the positioning tag, and determine the positioning UWB base station of the positioning area;

[0017] Determine the target positioning information according to the first time information in the positioning signal sent by the positioning tag;

[0018] Respectively determine the second time information for receiving the target positioning information in the positioning UWB base station;

[0019] Determine the time difference of arrival based on the first time information and the second time information;

[0020] Simultaneously obtain the third time information of the ranging signal sent by the positioning UWB base station in the positioning signal and the fourth time information of the positioning tag receiving the ranging signal;

[0021] Determine the time difference of departure according to the third time information and the fourth time information;

[0022] Determine the ranging information according to the time difference of arrival, the time difference of departure, and the propagation rate of the positioning signal;

[0023] Determine the local coordinate position of the target person according to the original ranging data, and obtain the initial three-dimensional coordinates based on the local coordinate position and the ranging information.

[0024] In one embodiment, the step of performing residual compensation on the initial three-dimensional coordinates through a convolutional neural network to obtain the corrected high-precision position coordinates includes:

[0025] Input the initial three-dimensional coordinates into the signal strength matrix in the convolutional neural network to obtain an input matrix;

[0026] Convolve the input matrix through four convolutional layers to obtain convolutional features;

[0027] Flatten the convolutional features to obtain a one-dimensional feature vector;

[0028] Pass the one-dimensional feature vector through two fully connected layers and an output layer to obtain a residual compensation amount;

[0029] Perform residual compensation on the initial three-dimensional coordinates based on the residual compensation amount to obtain corrected high-precision position coordinates.

[0030] In one embodiment, the UWB-based real-time positioning method for power plant personnel further includes:

[0031] Determine the access permission of the target person, and determine the permission area of the target person based on the Voronoi diagram,

[0032] Determine the regional boundary of the permission area, and determine the safety distance function according to the boundary area;

[0033] Determine the set of movable coordinates of the target person based on the access permission and the safety distance function, and generate an electronic fence area according to the set of movable coordinates.

[0034] In one embodiment, after the step of mapping the high-precision position coordinates to a three-dimensional visualization model, dynamically rendering the target person and the environmental scene, and determining the real-time position of the target person, the method further includes:

[0035] Obtain the historical position data of the target person, and extract the key time step features of the historical position data;

[0036] Input the key time step features into a trajectory prediction model to obtain the weight of each time step, and the trajectory prediction model is a bidirectional LSTM model;

[0037] Perform weighted combination on the key time step features based on the weights to obtain a target feature vector;

[0038] Perform fully connected activation on the target feature vector according to the trajectory prediction function to obtain a predicted motion trajectory.

[0039] In one embodiment, the step of inputting the key time step features into a trajectory prediction model to obtain the weight of each time step includes:

[0040] Determine the attention score of the key time step features based on the trajectory prediction model;

[0041] Determine the similarity between the hidden state of each key time step feature and the target query vector according to the attention score;

[0042] Determine the weight of the key time step features according to the similarity.

[0043] In one embodiment, before the step of fully connecting and activating the target feature vector according to the trajectory prediction function to obtain the predicted motion trajectory, the following steps are further included:

[0044] Determine UWB positioning data, and generate an observation matrix according to the UWB positioning data;

[0045] Determine UWB observation values according to the observation matrix and the UWB positioning data;

[0046] Determine a state transition matrix according to the positional change of the UWB positioning data in time series;

[0047] Determine a trajectory prediction function according to the UWB observation values, the state transition matrix, the observation matrix, and the Kalman gain.

[0048] In one embodiment, after the step of mapping the high-precision position coordinates to a three-dimensional visualization model, dynamically rendering the target person and the environmental scene, and determining the real-time position of the target person, the following steps are further included:

[0049] Generate a restricted area according to the dangerous area and the boundary area of the electronic fence area of the target person;

[0050] Determine the critical distance between the real-time position and the restricted area;

[0051] When the critical distance is less than a preset critical distance, trigger a first-level alarm message;

[0052] When the predicted motion trajectory of the target person enters the restricted area, trigger a second-level alarm message, and the alarm level of the first-level alarm message is greater than that of the second-level alarm message;

[0053] When the first-level alarm message or the second-level alarm message is triggered, record the identity information of the target person.

[0054] In addition, to achieve the above object, the present application further provides a real-time positioning device for power plant personnel based on UWB. The real-time positioning device for power plant personnel based on UWB includes:

[0055] A data acquisition module, configured to obtain the original ranging data of the target person through the communication data between the UWB base station network and the positioning tag;

[0056] A position fitting module, configured to calculate the initial three-dimensional coordinates based on the personnel positioning model according to the original ranging data;

[0057] A position correction module, configured to perform residual compensation on the initial three-dimensional coordinates through a convolutional neural network to obtain the corrected high-precision position coordinates;

[0058] A target positioning module, configured to map the high-precision position coordinates to a three-dimensional visualization model, dynamically render the target person and the environmental scene, and determine the real-time position of the target person.

[0059] In addition, to achieve the above object, the present application further provides a real-time positioning device for power plant personnel based on UWB. The real-time positioning device for power plant personnel based on UWB includes: a memory, a processor, and a computer program stored on the memory and executable on the processor. The computer program is configured to implement the steps of the above-mentioned real-time positioning method for power plant personnel based on UWB.

[0060] In addition, to achieve the above object, the present invention further provides a storage medium. The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the above-mentioned real-time positioning method for power plant personnel based on UWB are implemented.

[0061] In addition, to achieve the above object, the present application further provides a computer program product. The computer program product includes a computer program. When the computer program is executed by a processor, the steps of the above-mentioned real-time positioning method for power plant personnel based on UWB are implemented.

[0062] The present application provides a real-time positioning method for power plant personnel based on UWB. The original ranging data of the target person is obtained through the communication data between the UWB base station network and the positioning tag; based on the personnel positioning model, the initial three-dimensional coordinates are calculated according to the original ranging data; the initial three-dimensional coordinates are compensated for residuals through a convolutional neural network to obtain the corrected high-precision position coordinates; the high-precision position coordinates are mapped to a three-dimensional visualization model, and the target person and the environmental scene are dynamically rendered to determine the real-time position of the target person. By the above method, the technical problems in the prior art that the location of power plant personnel cannot be accurately positioned and the activity areas of power plant personnel cannot be monitored are solved. Description of the Drawings

[0063] The drawings here are incorporated into the description and form a part of this description, showing embodiments consistent with the present application and used together with the description to explain the principles of the present application.

[0064] To more clearly illustrate the technical solutions in the embodiments of the present application or in the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, for those of ordinary skill in the art, other drawings can also be obtained based on these drawings without creative efforts.

[0065] Figure 1 It is a schematic flowchart of the first embodiment of the real-time positioning method for power plant personnel based on UWB of the present application;

[0066] Figure 2 This is the original ranging schematic diagram of an embodiment of the UWB-based real-time positioning method for power plant personnel in this application;

[0067] Figure 3 This is the module structure schematic diagram of the UWB-based real-time positioning device for power plant personnel in an embodiment of this application;

[0068] Figure 4 This is the device structure schematic diagram of the hardware operating environment involved in the UWB-based real-time positioning method for power plant personnel in an embodiment of this application.

[0069] The realization of the purpose of this application, functional features, and advantages will be further described in conjunction with embodiments with reference to the accompanying drawings. Detailed implementation manners

[0070] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of this application and are not used to limit this application.

[0071] To better understand the technical solutions of this application, the following will be described in detail in conjunction with the accompanying drawings of the specification and specific implementation manners.

[0072] The main solution of the embodiment of this application is: obtaining the original ranging data of the target personnel through the communication data between the UWB base station network and the positioning tag; calculating the initial three-dimensional coordinates based on the personnel positioning model according to the original ranging data; performing residual compensation on the initial three-dimensional coordinates through a convolutional neural network to obtain the corrected high-precision position coordinates; mapping the high-precision position coordinates to a three-dimensional visualization model, dynamically rendering the target personnel and the environmental scene, and determining the real-time position of the target personnel.

[0073] Currently, traditional power plant personnel positioning systems mainly rely on RFID or Bluetooth technologies, and these technologies have obvious deficiencies in terms of positioning accuracy and anti-interference ability. The positioning accuracy of RFID technology is usually between 3 and 5 meters, and the positioning accuracy of Bluetooth technology is also roughly the same. Moreover, both are easily interfered by other wireless signals in the environment, resulting in inaccurate positioning. In addition, the existing systems lack the ability to analyze and predict personnel behavior and cannot effectively prevent personnel from entering dangerous areas. And the current two-dimensional positioning systems are difficult to accurately reflect the spatial characteristics in complex industrial environments, cannot accurately and real-time locate the positions of various identity types of personnel in the power plant, and cannot timely sense whether the power plant staff enter dangerous areas.

[0074] The present application provides a solution, which obtains the original ranging data of a target person through the communication data between a UWB base station network and a positioning tag; based on a personnel positioning model, calculates an initial three-dimensional coordinate according to the original ranging data; performs residual compensation on the initial three-dimensional coordinate through a convolutional neural network to obtain a corrected high-precision position coordinate; maps the high-precision position coordinate to a three-dimensional visualization model, dynamically renders the target person and the environmental scene, and determines the real-time position of the target person. By the above method, the technical problems in the prior art that the location of power plant personnel cannot be accurately located and the activity area of power plant personnel cannot be monitored are solved.

[0075] It should be noted that the execution subject of this embodiment can be a computing service device with data processing, network communication, and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device capable of implementing the above functions, a UWB-based real-time positioning device for power plant personnel, etc. This embodiment does not make specific limitations in this regard. Hereinafter, taking the UWB-based real-time positioning device for power plant personnel as an example, this embodiment and the following embodiments will be described.

[0076] The embodiment of the present application provides a UWB-based real-time positioning method for power plant personnel, referring to Figure 1 , Figure 1 which is a schematic flowchart of the first embodiment of the UWB-based real-time positioning method for power plant personnel of the present application.

[0077] In this embodiment, the UWB-based real-time positioning method for power plant personnel includes steps S10 to S40:

[0078] Step S10, obtaining the original ranging data of the target person through the communication data between the UWB base station network and the positioning tag;

[0079] It should be noted that the UWB base station network is a sensor network formed by signal receivers arranged in various areas of the power plant. The power plant personnel wear positioning tags that can send UWB signals at regular time intervals. In the area where the power plant personnel are located, the existing signal receivers can receive and process the UWB signal and interpret information such as the transmission time in the UWB signal. The original ranging information of the target person is the moment information when the UWB signal is received by the signal sensor and the transmission moment information interpreted from the UWB signal. According to the difference between these two moment information, the time required for the signal from transmission to reception can be determined. Since the UWB signal has a short transmission distance and relatively stable transmission quality in the power plant environment, the transmission speed basically does not change. Therefore, the straight-line distance between the signal emission point and the signal receiver can be determined based on the transmission speed of the UWB signal and the difference between the two moment information. And a UWB signal can be received by multiple signal receivers, so the original ranging data of the target person can be determined based on multiple signal receivers. Refer to Figure 2 , Figure 2 is the schematic diagram of the original ranging. Among them, l1 to l4 are the original ranging data of the signal receivers u1 to u4 respectively.

[0080] In a specific implementation, when a positioning signal of a positioning tag is detected in a UWB base station network, the positioning signal is recorded; when the positioning signal is within the detection range of the UWB base station network, the real-time distance between the positioning signal and the UWB base station can be determined at a preset detection period; the positioning signal and the real-time distance are mapped to the local coordinate system corresponding to the UWB base station to determine the local coordinate position of the positioning signal in the local coordinate system; the local coordinate positions are sorted based on the time stamp sequence of the detection period to generate original ranging data. Specifically: The signal receiver in the UWB base station network can monitor the UWB signals in the environment and capture the positioning signals sent by the positioning tags in the environment. When receiving such a positioning signal, this positioning signal can be recorded. The positioning signal contains permission information or identity information of the positioning tag, etc. When the positioning signal enters the detection range of the UWB base station network, the real-time distance between the positioning signal and the UWB base station can be determined at a preset detection period. Through the real-time distances of multiple UWB base stations, multi-point positioning can be achieved to obtain a determined area, which is the position of the power plant personnel carrying the positioning tag. When determining the position, the more UWB base stations involved, the more accurate the located position. After determining the real-time distance, the positioning signal and the predicted real-time distance can be mapped to the local coordinate system corresponding to the UWB base station, and the local coordinate position of the positioning signal in the local coordinate system can be determined. Then, the local coordinate positions are sorted according to the time stamp sequence in the detection period, and the original ranging information of the positioning signal in the current UWB base station can be determined.

[0081] Step S20, based on the personnel positioning model, calculate the initial three-dimensional coordinates according to the original ranging data;

[0082] It should be noted that the personnel positioning model is constructed based on an improved TW-TOA algorithm. Compared with the traditional TW-TOA algorithm, the improved TW-TOA algorithm improves the high-precision positioning in complex environments through methods such as robust estimation. The initial three-dimensional coordinates are a data-based description of the location of the power plant personnel, that is, a coordinate system is established for the area where they are located, and the position of the power plant personnel is described in the form of coordinates.

[0083] It can be understood that when calculating the initial three-dimensional coordinates based on the personnel positioning model according to the original ranging data, the positioning area of the target personnel can be determined according to the positioning tag, and the positioning UWB base station in the positioning area can be determined; the target positioning information can be determined according to the first time information in the positioning signal sent by the positioning tag; the second time information for receiving the target positioning information can be determined in the positioning UWB base station respectively; the time difference of arrival direction can be determined based on the first time information and the second time information; at the same time, the third time information of the ranging signal sent by the positioning UWB base station in the positioning signal and the fourth time information of the positioning tag receiving the ranging signal can be obtained; the time difference of departure direction can be determined according to the third time information and the fourth time information; the ranging information can be determined according to the time difference of arrival direction, the time difference of departure direction, and the propagation rate of the positioning signal; the local coordinate position of the target personnel can be determined according to the original ranging data, and the initial three-dimensional coordinates can be obtained based on the local coordinate position and the ranging information.

[0084] It should be noted that UWB signals are sent between the positioning tag and the UWB base station to confirm the position. In the positioning signal, the reception time of the signal sent by the UWB base station received by the positioning tag most recently and the transmission time of the positioning signal can be included. Therefore, it can be understood that the UWB base station sends a UWB signal A at time t1, then the positioning tag receives the UWB signal A at time t2, then the positioning tag sends a positioning signal at time t3, and the positioning signal includes the information that the UWB signal A was received at time t2, and then the UWB base station receives the positioning signal at time t4. Based on this, the time difference of arrival direction and the time difference of departure direction can be obtained, and then the ranging information can be determined according to the transmission rate of the signal. Then, the local coordinate position of the target personnel can be determined according to the ranging information, and the initial three-dimensional coordinates can be obtained based on the local coordinate position and the ranging information. Among them, when unifying the local coordinate system and the global coordinate system, the coordinate unification can be realized by means of mapping. The specific mapping relationship is:

[0085]

[0086] Among them, R is the rotation matrix, T is the translation vector, X g , Y g , Z g are the corresponding coordinate values in the global coordinate system, and X t , Y t , Z t are the corresponding coordinate values in the local coordinate system.

[0087] Step S30, perform residual compensation on the initial three-dimensional coordinates through a convolutional neural network to obtain the corrected high-precision position coordinates;

[0088] In a specific implementation, when performing residual compensation on the initial three-dimensional coordinates through a convolutional neural network, the initial three-dimensional coordinates can be input into the signal strength matrix in the convolutional neural network to obtain an input matrix; the input matrix is convolved through four convolutional layers to obtain convolutional features; the convolutional features are flattened to obtain a one-dimensional feature vector; the one-dimensional feature vector passes through two fully connected layers and an output layer to obtain a residual compensation amount; based on the residual compensation amount, residual compensation is performed on the initial three-dimensional coordinates to obtain corrected high-precision position coordinates. Among them, the input layer is an 8×8 UWB signal strength matrix, and then it is successively convolved through 4 convolutional layers and 2 fully connected layers. The convolutional layer extracts features from the input matrix through a convolutional kernel, and each convolutional layer can extract features at different levels. The convolutional features are flattened to obtain a one-dimensional feature vector. The flattening operation converts the multi-dimensional feature map into a one-dimensional vector for input into the fully connected layer. The one-dimensional feature vector passes through two fully connected layers and an output layer to obtain a residual compensation amount. The fully connected layer further processes the extracted features, and the output layer generates the final residual compensation amount. The output three-dimensional coordinate residual compensation amount is expressed as Δx, Δy, Δz, and the final coordinates after compensation are: (x′, y′, z′) = (x0 + Δx, y0 + Δy, z0 + Δz).

[0089] Step S40: Map the high-precision position coordinates to a three-dimensional visualization model, dynamically render the target person and the environmental scene, and determine the real-time position of the target person.

[0090] It can be understood that when mapping the high-precision position coordinates to a three-dimensional visualization model and dynamically rendering the target person and the environmental scene, first, the coordinate system of the three-dimensional visualization model needs to be corresponding to the coordinate system in the actual scene, including relevant environmental factors such as buildings and equipment, so as to accurately reflect the actual position of the target person. After the coordinates are aligned, dynamic rendering can be performed. At this time, it can be processed by the method of frame interpolation, and interpolation is performed on discrete position sampling points, which can be specifically expressed as:

[0091]

[0092] where P(t) is the target position at the current time t, and are the positions at adjacent timestamps, t0 is the initial time, t1 is the next time point, is the time ratio.

[0093] The movement trajectory of the target person in the model can be predicted through Kalman filtering or particle filtering, specifically as:

[0094]

[0095] Among them, is the predicted state of the target person, is the state estimate of the predicted state of the target person at the previous moment, z k is the measurement value at time step k, A is the state transition matrix, H is the observation matrix, B is the control input matrix, u k is the input vector, ω k and v k are noises.

[0096] After completing the dynamic rendering, it can update the performance states of the target person and the environment in the 3D visualization model in real time, so as to determine the real-time position of the target person.

[0097] In a feasible implementation manner, the UWB-based real-time positioning method for power plant personnel further includes:

[0098] Determine the access permission of the target person, and determine the permission area of the target person based on the Voronoi diagram,

[0099] Determine the regional boundary of the permission area, and determine the safety distance function according to the boundary area;

[0100] Determine the set of movable coordinates of the target person based on the access permission and the safety distance function, and generate an electronic fence area according to the set of movable coordinates.

[0101] In a specific implementation, first determine the communication permission of the target person. The areas that can be accessed by personnel with different identities are different. For example, in some high-voltage areas, only relevant professional and technical personnel can enter, otherwise it is easy to cause safety accidents. Therefore, the power plant space can be divided into several permission areas, and each area corresponds to a control point (such as an access control point, a safety node). Then, divide the power plant environment according to the Voronoi diagram, which is specifically expressed as: given a set of control point sets P = {p1, p2,..., p n}, and the Voronoi region V(p i ) generated by each control point p i is defined as:

[0102]

[0103] where d(x, p i ) is the Euclidean distance from point x to p i .

[0104] Then extract the regional boundary from the Voronoi diagram. The edges of the Voronoi diagram are shared by adjacent regions, and the set E of the boundaries is:

[0105]

[0106] Define the distance from the position q of the target person to the nearest boundary as the safety distance function SDF(q):

[0107]

[0108] Among them, d(q, e) represents the distance e from the position q of the target person to the boundary.

[0109] Combining the access permission and the safety distance, the coordinate range of allowed activities can be determined. If the target person belongs to the authorized object in the area V(p i ), its activity range is restricted within V(p i ). Superimposing the safety distance constraint, the effective activity area A valid can be obtained:

[0110] A valid = {q ∈ V(p i ) | SDF(q) ≥ r threshold}

[0111] Among them, r threshold is the safety distance threshold.

[0112] Then generate an electronic fence area according to the set of movable coordinates.

[0113] In a feasible implementation manner, after the step of mapping the high-precision position coordinates to the three-dimensional visualization model, dynamically rendering the target person and the environmental scene, and determining the real-time position of the target person, the following steps are further included:

[0114] Obtain the historical position data of the target person, and extract the key time step features of the historical position data;

[0115] Based on the trajectory prediction model, determine the attention score of the key time step features, and the trajectory prediction model is a bidirectional LSTM model;

[0116] According to the attention score, determine the similarity between the hidden state of each key time step feature and the target query vector;

[0117] According to the similarity, determine the weight of the key time step feature;

[0118] Based on the weight, perform weighted combination on the key time step features to obtain a target feature vector;

[0119] According to the trajectory prediction function, perform fully connected activation on the target feature vector to obtain a predicted motion trajectory.

[0120] In a specific implementation, historical location data of a target person can be obtained, and key time-step features including speed, acceleration, direction angle, etc. can be determined based on the historical location data. Then, the attention scores of the key time-step features are determined according to a trajectory prediction model, where the trajectory prediction model is a bidirectional LSTM model. The target query vector is determined based on the key time-step features, and the attention scores are determined through similarity, and the similarity s t can be expressed as:

[0121] s t = q Τ ·h t

[0122] where q is the target query vector, and h t is the hidden state of the bidirectional LSTM model.

[0123] The weight α of the key time-step features is determined according to the similarity t , and the calculation formula is:

[0124]

[0125] Then, by weighted summing the hidden states, the key time-step information is captured to obtain the target feature vector c:

[0126]

[0127] where α t is the weight at time step t, and R 2h is the dimension of the target feature vector.

[0128] The target feature vector is fully connected and activated according to the trajectory prediction function to obtain the predicted motion trajectory. The fully connected layer maps the context vector to the future position The mapping relationship is:

[0129]

[0130] where W ∈ R (k×d)·2h is the weight matrix, b ∈ R k×d is the bias term, and k is the number of predicted future time steps.

[0131] In a feasible implementation manner, before the step of fully connecting and activating the target feature vector according to the trajectory prediction function to obtain the predicted motion trajectory, it further includes:

[0132] Determine the UWB positioning data, and generate an observation matrix according to the UWB positioning data;

[0133] Determine the UWB observation value according to the observation matrix and the UWB positioning data;

[0134] Determine the state transition matrix according to the change in the position of the UWB positioning data over time;

[0135] Determine the trajectory prediction function according to the UWB observation value, the state transition matrix, the observation matrix, and the Kalman gain.

[0136] In a specific implementation, it is possible to determine the UWB positioning data, generate an observation matrix according to the UWB positioning data, determine the UWB observation value according to the observation matrix and the UWB positioning data; determine the state transition matrix according to the change in the position of the UWB positioning data over time; determine the trajectory prediction function according to the UWB observation value, the state transition matrix, the observation matrix, and the Kalman gain. The specific formula is:

[0137]

[0138] where, F k is the state transition matrix, K k is the Kalman gain, z k is the UWB observation value.

[0139] In a feasible implementation manner, after the step of mapping the high-precision position coordinates to the three-dimensional visualization model, dynamically rendering the target person and the environmental scene, and determining the real-time position of the target person, the following steps are further included:

[0140] Generate a restricted area according to the dangerous area and the boundary area of the electronic fence area of the target person;

[0141] Determine the critical distance between the real-time position and the restricted area;

[0142] When the critical distance is less than the preset critical distance, trigger a first-level alarm message;

[0143] When the predicted movement trajectory of the target person enters the restricted area, trigger a second-level alarm message, and the alarm level of the first-level alarm message is greater than that of the second-level alarm message;

[0144] When the first-level alarm message or the second-level alarm message is triggered, record the identity information of the target person.

[0145] In a specific implementation, a restricted area is generated based on the boundary area between the hazardous area and the electronic fence area of the target person. The restricted area is a key area that needs to be monitored to ensure that the target person does not enter the hazardous area. Then, the critical distance between the real-time position and the restricted area is determined. When the critical distance is less than the preset critical distance, it indicates that the restricted area is about to be approached, so a first-level alarm message can be triggered. If the predicted movement trajectory of the target person enters the restricted area, a second-level alarm message is triggered, indicating that the target person may enter the restricted area. Among them, the alarm level of the first-level alarm message is greater than that of the second-level alarm message.

[0146] This embodiment provides a real-time positioning method for power plant personnel based on UWB. The original ranging data of the target person is obtained through the communication data between the UWB base station network and the positioning tag; based on the personnel positioning model, the initial three-dimensional coordinates are calculated according to the original ranging data; the initial three-dimensional coordinates are compensated for residuals through a convolutional neural network to obtain the corrected high-precision position coordinates; the high-precision position coordinates are mapped to a three-dimensional visualization model, and the target person and the environmental scene are dynamically rendered to determine the real-time position of the target person. In this way, the technical problems in the prior art of being unable to accurately locate the location of power plant personnel and monitor the activity area of power plant personnel are solved.

[0147] It should be noted that the above examples are only for understanding this application and do not constitute a limitation to the real-time positioning method for power plant personnel based on UWB in this application. Based on this technical concept, more forms of simple transformations are within the protection scope of this application.

[0148] This application also provides a real-time positioning device for power plant personnel based on UWB. Please refer to Figure 3 , the real-time positioning device for power plant personnel based on UWB includes:

[0149] The data acquisition module 10 is used to obtain the original ranging data of the target person through the communication data between the UWB base station network and the positioning tag;

[0150] The position fitting module 20 is used to calculate the initial three-dimensional coordinates according to the original ranging data based on the personnel positioning model;

[0151] The position correction module 30 is used to compensate for the residuals of the initial three-dimensional coordinates through a convolutional neural network to obtain the corrected high-precision position coordinates;

[0152] The target positioning module 40 is used to map the high-precision position coordinates to a three-dimensional visualization model, dynamically render the target person and the environmental scene, and determine the real-time position of the target person.

[0153] In a feasible implementation manner, the data acquisition module 10 is further configured to record the positioning signal when the positioning signal of the positioning tag is detected in the UWB base station network; when the positioning signal is within the detection range of the UWB base station network, determine the real-time distance between the positioning signal and the UWB base station at a preset detection period; map the positioning signal and the real-time distance to the local coordinate system corresponding to the UWB base station, and determine the local coordinate position of the positioning signal in the local coordinate system; sort the local coordinate positions based on the time stamp sequence of the detection period to generate the original ranging data.

[0154] In a feasible implementation manner, the position fitting module 20 is further configured to determine the positioning area of the target person according to the positioning tag, and determine the positioning UWB base station of the positioning area; determine the target positioning information according to the first time information in the positioning signal sent by the positioning tag; respectively determine the second time information for receiving the target positioning information in the positioning UWB base station; determine the time difference of arrival based on the first time information and the second time information; simultaneously obtain the third time information of the ranging signal sent by the positioning UWB base station in the positioning signal and the fourth time information when the positioning tag receives the ranging signal; determine the time difference of departure according to the third time information and the fourth time information; determine the ranging information according to the time difference of arrival, the time difference of departure, and the propagation rate of the positioning signal; determine the local coordinate position of the target person according to the original ranging data, and obtain the initial three-dimensional coordinates based on the local coordinate position and the ranging information.

[0155] In a feasible implementation manner, the position correction module 30 is further configured to input the initial three-dimensional coordinates into the signal strength matrix in the convolutional neural network to obtain an input matrix; perform convolution on the input matrix through four convolutional layers to obtain convolution features; flatten the convolution features to obtain a one-dimensional feature vector; pass the one-dimensional feature vector through two fully connected layers and an output layer to obtain a residual compensation amount; perform residual compensation on the initial three-dimensional coordinates based on the residual compensation amount to obtain the corrected high-precision position coordinates.

[0156] In a feasible implementation manner, the target positioning module 40 is further configured to determine the access permission of the target person, determine the permission area of the target person based on the Voronoi diagram, determine the area boundary of the permission area, and determine the safety distance function according to the boundary area; determine the set of movable coordinates of the target person based on the access permission and the safety distance function, and generate an electronic fence area according to the set of movable coordinates.

[0157] In a feasible implementation manner, the target positioning module 40 is further configured to obtain the historical location data of the target person, and extract the key time step features of the historical location data; input the key time step features into a trajectory prediction model to obtain the weights of each time step, where the trajectory prediction model is a bidirectional LSTM model; perform weighted combination on the key time step features based on the weights to obtain a target feature vector; perform fully connected activation on the target feature vector according to a trajectory prediction function to obtain a predicted motion trajectory.

[0158] In a feasible implementation manner, the target positioning module 40 is further configured to determine the attention scores of the key time step features based on the trajectory prediction model; determine the similarity between the hidden state of each key time step feature and a target query vector according to the attention scores; determine the weights of the key time step features according to the similarity.

[0159] In a feasible implementation manner, the target positioning module 40 is further configured to determine UWB positioning data, generate an observation matrix according to the UWB positioning data; determine UWB observation values according to the observation matrix and the UWB positioning data; determine a state transition matrix according to the position change of the UWB positioning data in time series; determine a trajectory prediction function according to the UWB observation values, the state transition matrix, the observation matrix, and the Kalman gain.

[0160] In a feasible implementation manner, the target positioning module 40 is further configured to generate a restricted area according to the dangerous area and the boundary area of the electronic fence area of the target person;

[0161] Determine the critical distance between the real-time position and the restricted area; trigger a first-level alarm message when the critical distance is less than a preset critical distance; trigger a second-level alarm message when the predicted motion trajectory of the target person enters the restricted area, where the alarm level of the first-level alarm message is greater than that of the second-level alarm message; record the identity information of the target person when the first-level alarm message or the second-level alarm message is triggered.

[0162] The UWB-based real-time positioning device for power plant personnel provided by this application adopts the UWB-based real-time positioning method for power plant personnel in the above embodiments, and can solve the technical problems of being unable to accurately locate the location of power plant personnel and monitor the activity areas of power plant personnel. Compared with the prior art, the beneficial effects of the UWB-based real-time positioning device for power plant personnel provided by this application are the same as those of the UWB-based real-time positioning method for power plant personnel provided by the above embodiments, and other technical features in the UWB-based real-time positioning device for power plant personnel are the same as the features disclosed in the above embodiment method, and will not be elaborated here.

[0163] The present application provides a real-time positioning device for power plant personnel based on UWB. The real-time positioning device for power plant personnel based on UWB includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable 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 execute the real-time positioning method for power plant personnel based on UWB in Embodiment 1 above.

[0164] Reference is made below Figure 4 , which shows a schematic structural diagram of a real-time positioning device for power plant personnel based on UWB suitable for implementing the embodiments of the present application. The real-time positioning device for power plant personnel based on UWB in the embodiments of the present application may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions: tablet computers), PMPs (Portable Media Players), in-vehicle terminals (such as in-vehicle navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 4 The real-time positioning device for power plant personnel based on UWB shown is merely an example and should not impose any limitations on the functions and usage scope of the embodiments of the present application.

[0165] As Figure 4As shown, the UWB-based real-time personnel positioning device in a power plant may include a processing device 1001 (such as a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 into a random access memory (RAM: Random Access Memory) 1004. In the RAM 1004, various programs and data required for the operation of the UWB-based real-time personnel positioning device in a power plant are also stored. The processing device 1001, the ROM 1002, and the RAM 1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems may be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the UWB-based real-time personnel positioning device in a power plant to communicate with other devices wirelessly or wiredly to exchange data. Although the figure shows a UWB-based real-time personnel positioning device with various systems, it should be understood that it is not required to implement or have all the shown systems. More or fewer systems may be alternatively implemented or had.

[0166] In particular, according to the embodiments disclosed in the present application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program codes for performing the methods shown in the flowcharts. In such an embodiment, the computer program can be downloaded and installed from a network through the communication device, or installed from the storage device 1003, or installed from the ROM 1002. When the computer program is executed by the processing device 1001, the above functions defined in the methods of the embodiments disclosed in the present application are executed.

[0167] The real-time positioning device for power plant personnel based on UWB provided by this application adopts the real-time positioning method for power plant personnel based on UWB in the above-mentioned embodiment, and can solve the technical problems of real-time positioning of power plant personnel based on UWB. Compared with the prior art, the beneficial effects of the real-time positioning device for power plant personnel based on UWB provided by this application are the same as those of the real-time positioning method for power plant personnel based on UWB provided by the above-mentioned embodiment, and other technical features in the real-time positioning device for power plant personnel based on UWB are the same as those disclosed in the method of the previous embodiment, which will not be elaborated here.

[0168] It should be understood that each part disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in a suitable manner in any one or more embodiments or examples.

[0169] The above is only the specific implementation manner of this application, but the protection scope of this application is not limited thereto. Any person skilled in the art within the technical scope disclosed in this application can easily think of changes or substitutions, which should all be covered within the protection scope of this application. Therefore, the protection scope of this application shall be subject to the protection scope of the claims.

[0170] This application provides a computer-readable storage medium with computer-readable program instructions (i.e., computer programs) stored thereon, and the computer-readable program instructions are used to execute the real-time positioning method for power plant personnel based on UWB in the above-mentioned embodiment.

[0171] The computer-readable storage medium provided by this application can be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or components, or any combination of the above. More specific examples of computer-readable storage media can include, but are not limited to: electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM) or flash memory, optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above. In this embodiment, the computer-readable storage medium can be any tangible medium that contains or stores a program, and this program can be used by or in combination with an instruction execution system, device, or component. The program code contained on the computer-readable storage medium can be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0172] The above computer-readable storage medium can be included in the UWB-based real-time personnel positioning device in a power plant; it can also exist independently and not be assembled into the UWB-based real-time personnel positioning device in a power plant.

[0173] The above computer-readable storage medium carries one or more programs. When the above one or more programs are executed by the UWB-based real-time personnel positioning device in a power plant, the UWB-based real-time personnel positioning device is enabled to: obtain the original ranging data of the target personnel through the communication data between the UWB base station network and the positioning tag; calculate the initial three-dimensional coordinates based on the personnel positioning model according to the original ranging data; perform residual compensation on the initial three-dimensional coordinates through a convolutional neural network to obtain the corrected high-precision position coordinates; map the high-precision position coordinates to a three-dimensional visualization model, dynamically render the target personnel and the environmental scene, and determine the real-time position of the target personnel.

[0174] Computer program code for performing the operations of this application can be written in one or more programming languages or combinations thereof. The above-mentioned programming languages include object-oriented programming languages such as Java, Smalltalk, C++, and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, executed as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (for example, by connecting through the Internet using an Internet service provider).

[0175] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in the flowchart or block diagram can represent a module, a program segment, or a part of the code, and this module, program segment, or part of the code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than that marked in the accompanying drawings. For example, two consecutively represented blocks can actually be executed substantially in parallel, and they can sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, as well as the combination of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0176] The modules described in the embodiments of this application can be implemented in software or in hardware. Among them, the name of the module does not constitute a limitation on the unit itself in some cases.

[0177] The readable storage medium provided by this application is a computer-readable storage medium. The computer-readable storage medium stores computer-readable program instructions (i.e., computer programs) for performing the above-mentioned UWB-based real-time positioning method for power plant personnel, and can solve the technical problems of UWB-based real-time positioning of power plant personnel. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by this application are the same as those of the UWB-based real-time positioning method for power plant personnel provided by the above embodiments, and will not be elaborated here.

[0178] The present application also provides a computer program product, including a computer program, which implements the steps of the above-mentioned UWB-based real-time positioning method for power plant personnel when executed by a processor.

[0179] The computer program product provided by the present application can solve the technical problems of UWB-based real-time positioning of power plant personnel. Compared with the prior art, the beneficial effects of the computer program product provided by the present application are the same as those of the UWB-based real-time positioning method for power plant personnel provided in the above embodiments, and will not be elaborated here.

[0180] The above are only partial embodiments of the present application, and thus do not limit the patent scope of the present application. Any equivalent structural transformation made under the technical concept of the present application by using the content of the specification and drawings of the present application, or direct / indirect application in other related technical fields, is included in the patent protection scope of the present application.

Claims

1. A real-time positioning method for power plant personnel based on UWB, characterized in that: The UWB-based real-time positioning method for power plant personnel includes: The original distance measurement data of the target person is obtained through the communication data between the UWB base station network and the positioning tag; Based on the personnel positioning model, initial three-dimensional coordinates are calculated according to the original ranging data; Performing residual compensation on the initial three-dimensional coordinates through a convolutional neural network to obtain corrected high-precision position coordinates; The high-precision position coordinates are mapped to a three-dimensional visualization model, the target person and the environmental scene are dynamically rendered, and the real-time position of the target person is determined.

2. The method according to claim 1, characterized in that The step of obtaining the original distance measurement data of the target person through the communication data between the UWB base station network and the positioning tag includes: When a positioning signal of a positioning tag is detected in a UWB base station network, the positioning signal is recorded; When the positioning signal is within the detection range of the UWB base station network, the real-time distance between the positioning signal and the UWB base station can be determined in a preset detection period; Mapping the positioning signal and the real-time distance to a local coordinate system corresponding to the UWB base station, and determining a local coordinate position of the positioning signal in the local coordinate system; The local coordinate positions are sorted based on the timestamp sequence of the detection period to generate raw ranging data.

3. The method according to claim 1, characterized in that The step of calculating the initial three-dimensional coordinates based on the original distance measurement data based on the personnel positioning model comprises: Determine the positioning area of ​​the target person according to the positioning tag, and determine the positioning UWB base station of the positioning area; Determining target positioning information according to the first time information in the positioning signal sent by the positioning tag; Determine, in the positioning UWB base station respectively, second time information of receiving the target positioning information; Determine an incoming time difference based on the first time information and the second time information; Simultaneously acquiring the third time information of the ranging signal sent by the positioning UWB base station in the positioning signal and the fourth time information of the positioning tag receiving the ranging signal; Determine a destination time difference according to the third time information and the fourth time information; Determine the ranging information according to the incoming time difference and the outgoing time difference, and a propagation rate of the positioning signal; The local coordinate position of the target person is determined according to the original ranging data, and the initial three-dimensional coordinates are obtained based on the local coordinate position and the ranging information.

4. The method according to claim 1, characterized in that The step of performing residual compensation on the initial three-dimensional coordinates through a convolutional neural network to obtain corrected high-precision position coordinates comprises: Inputting the initial three-dimensional coordinates into a signal intensity matrix in the convolutional neural network to obtain an input matrix; Convolve the input matrix through four convolutional layers to obtain convolution features; Flatten the convolutional features to obtain a one-dimensional feature vector; Passing the one-dimensional feature vector through two fully connected layers and an output layer to obtain a residual compensation amount; The initial three-dimensional coordinates are subjected to residual compensation based on the residual compensation amount to obtain corrected high-precision position coordinates.

5. The method according to claim 1, characterized in that The UWB-based real-time positioning method for power plant personnel also includes: Determine the access rights of the target person, and determine the permission area of ​​the target person based on the Voronoi diagram, Determine the area boundary of the authority area, and determine the safety distance function according to the boundary area; Determine a movable coordinate set of the target person based on the access authority and the safety distance function; An electronic fence area is generated according to the movable coordinate set.

6. The method according to any one of claims 1 to 5, characterized in that After the step of mapping the high-precision position coordinates to a three-dimensional visualization model, dynamically rendering the target person and the environment scene, and determining the real-time position of the target person, the method further includes: Acquire the historical location data of the target person, and extract key time step features of the historical location data; Inputting the key time step features into a trajectory prediction model to obtain the weight of each time step, wherein the trajectory prediction model is a bidirectional LSTM model; Performing weighted combination on the key time step features based on the weights to obtain a target feature vector; The target feature vector is fully connected and activated according to the trajectory prediction function to obtain a predicted motion trajectory.

7. The method according to claim 6, characterized in that The step of inputting the key time step features into the trajectory prediction model to obtain the weight of each time step includes: Determining an attention score of the key time step feature based on the trajectory prediction model; Determine the similarity between the hidden state of each of the key time step features and the target query vector according to the attention score; The weight of the key time step feature is determined according to the similarity.

8. The method according to claim 6, characterized in that Before the step of fully connecting and activating the target feature vector according to the trajectory prediction function to obtain the predicted motion trajectory, the step further includes: Determine UWB positioning data, and generate an observation matrix according to the UWB positioning data; Determine a UWB observation value according to the observation matrix and the UWB positioning data; Determine a state transfer matrix according to a position change of the UWB positioning data in time sequence; A trajectory prediction function is determined according to the UWB observation value, the state transfer matrix, the observation matrix and the Kalman gain.

9. The method according to claim 1, characterized in that After the step of mapping the high-precision position coordinates to a three-dimensional visualization model, dynamically rendering the target person and the environment scene, and determining the real-time position of the target person, the method further includes: Generate a restricted area based on the boundary area of ​​the dangerous area and the electronic fence area of ​​the target person; Determining a critical distance between the real-time position and the restricted area; When the critical distance is less than the preset critical distance, a first-level alarm message is triggered; When the predicted movement trajectory of the target person enters the restricted area, a second-level alarm message is triggered, and the alarm level of the first-level alarm message is greater than the alarm level of the second-level alarm message; When the first-level alarm information or the second-level alarm information is triggered, the identity information of the target person is recorded.

10. A UWB-based real-time positioning device for power plant personnel, characterized in that: The UWB-based real-time positioning device for power plant personnel includes: A data acquisition module is used to acquire the original ranging data of the target person through the communication data between the UWB base station network and the positioning tag; A position fitting module, used to calculate the initial three-dimensional coordinates according to the original ranging data based on the personnel positioning model; A position correction module, used to perform residual compensation on the initial three-dimensional coordinates through a convolutional neural network to obtain corrected high-precision position coordinates; The target positioning module is used to map the high-precision position coordinates to a three-dimensional visualization model, dynamically render the target person and the environmental scene, and determine the real-time position of the target person.

Images