Temporary grounding wire positioning management method and system based on remote radio frequency technology

Abstract

The invention discloses a temporary grounding wire positioning management method and system based on a remote radio frequency technology, and relates to the technical field of temporary grounding wire positioning management, and the method comprises the steps: collecting the related data of a temporary grounding wire, and constructing a temporary grounding wire positioning management model; constructing a deep neural network model, and generating a virtual ground wire management scene; and using early warning and management of the temporary grounding wire are carried out in combination with the temporary grounding wire intelligent management model and the virtual grounding wire management scene. According to the invention, by collecting the multi-dimensional data and constructing the complex mathematical model, comprehensive quantitative evaluation of the state of the ground wire is realized, and the management accuracy and reliability are improved. And a virtual management scene is generated by using the deep neural network, so that the insight ability of managers is enhanced. And in combination with an intelligent management model and a virtual scene, a multi-level early warning and management system is established, and potential safety hazards are effectively reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of temporary grounding wire positioning management, and in particular to a temporary grounding wire positioning management method and system based on remote radio frequency technology. Background Art

[0002] As a key device for the safe operation of the power system, the management and monitoring of temporary grounding wires has always been an important topic in the power industry. With the rapid development of smart grid and Internet of Things technologies, the application of remote radio frequency identification (RFID) technology in power equipment management is becoming more and more widespread. Traditional temporary grounding wire management methods mainly rely on manual inspections and paper records, which is not only inefficient but also prone to human errors. In recent years, although some power companies have begun to adopt technologies such as barcodes or QR codes for grounding wire management, these methods still require manual intervention and cannot achieve real-time and dynamic monitoring. In addition, with the expansion of the scale and complexity of the power system, traditional management methods are difficult to cope with the increasing safety risks and management pressures.

[0003] There are many shortcomings in the existing temporary grounding wire management technology. First, it lacks real-time positioning and status monitoring capabilities, and is unable to promptly detect and deal with potential safety hazards. Secondly, it is difficult for existing technologies to effectively integrate and analyze massive amounts of historical data and real-time data, and cannot provide strong support for management decisions. Furthermore, traditional methods cannot generate virtual management scenarios, making it difficult to conduct early warnings and risk assessments. In addition, existing technologies often ignore the impact of the complexity of power plant layouts, environmental factors, and other factors on grounding wire management, resulting in unsatisfactory management results. Finally, the lack of intelligent and automated management methods makes it difficult to adapt to the efficient and refined management needs of modern power systems. Summary of the invention

[0004] In view of the fact that the above-mentioned temporary grounding wire management technology faces the problems of unsatisfactory real-time monitoring, intelligent early warning and risk assessment, the present invention is proposed.

[0005] Therefore, the technical problem solved by the present invention is: combining advanced technologies such as remote radio frequency identification, deep learning, and time series analysis to achieve real-time positioning, status monitoring, intelligent early warning, and risk assessment of temporary grounding wires.

[0006] To solve the above technical problems, the present invention provides the following technical solutions: a temporary grounding wire positioning management method based on remote radio frequency technology, comprising: collecting temporary grounding wire related data and constructing a temporary grounding wire positioning management model; constructing a deep neural network model to generate a virtual grounding wire management scenario; combining the temporary grounding wire intelligent management model and the virtual grounding wire management scenario to perform temporary grounding wire usage warning and management.

[0007] As a preferred solution of the temporary grounding wire positioning management method based on remote radio frequency technology of the present invention, the temporary grounding wire related data includes real-time data and historical data, the real-time data includes radio frequency identification data, environmental data, location data, usage status data and locking accessory status data; the historical data includes power plant layout data, historical usage frequency data and usage time fluctuation data.

[0008] As a preferred solution of the temporary grounding wire positioning management method based on remote radio frequency technology of the present invention, wherein: constructing a temporary grounding wire positioning management model includes calculating a comprehensive evaluation factor based on radio frequency identification data, environmental data, usage status data and locking accessory status, and the calculation formula of the comprehensive evaluation factor is as follows:

[0009]

[0010] Among them, F(t) is a comprehensive evaluation factor, which represents the comprehensive performance status of the grounding wire at time t, S(τ) represents the RF signal strength, E(τ) represents the environmental factor, U(τ) represents the use status of the grounding wire, C(τ) represents the locking accessory status, τ represents the integral variable, w1, w2 and w3 are all weight coefficients, α represents the environmental impact adjustment parameter, and λ1 is the power adjustment function; the spatial distribution factor is calculated in combination with the layout complexity and spatial distance. The calculation formula of the spatial distribution factor is as follows:

[0011]

[0012] Among them, D(x,y) is the spatial distribution factor, which represents the spatial distribution influence of the grounding wire at the position (x,y), L(.) represents the layout complexity, which represents the complexity of the power plant layout at the point (ξ,η); ξ and η are both integral variables, representing the coordinates of any point in the power plant; A represents the entire power plant area, and ∈ represents a small constant; through time series analysis, the historical data is converted into the usage mode factor, and the calculation formula of the usage mode factor is as follows:

[0013] P(t)=β1·ARIMA(H(t))+β2·GARCH(V(t))

[0014] Among them, P(t) represents the usage mode factor, which indicates the usage mode status of the grounding wire at time t, H(t) represents the historical usage frequency of the grounding wire, V(t) represents the volatility of the usage time of the grounding wire, ARIMA(.) represents the autoregressive integrated moving average model, which is used for time series prediction of historical usage frequency; GARCH(.) represents the generalized autoregressive conditional heteroskedasticity model, which is used for time series prediction of usage time volatility; β1 and β2 both represent weight coefficients, which are used to adjust the importance of the ARIMA model and the weight of the GARCH model respectively; the temporary grounding wire positioning management model is obtained by weighted combination of comprehensive evaluation factors, spatial distribution factors and usage mode factors. The calculation formula of the temporary grounding wire positioning management model is as follows:

[0015]

[0016] Wherein, M(x, y, t) is the evaluation value of the temporary grounding wire location management model, which represents the comprehensive evaluation status of the grounding wire at time t and position (x, y); γ1, γ2 and γ3 are all weight coefficients. Represents the rate of change of the comprehensive evaluation factor.

[0017] As a preferred solution of the temporary grounding wire positioning management method based on remote radio frequency technology of the present invention, generating a virtual grounding wire management scenario includes constructing a deep neural network model, including an encoder and a decoder; the encoder receives real-time data, historical records, and the evaluation value of the temporary grounding wire positioning management model as input, and extracts features through multi-layer convolution and recurrent neural networks; the decoder generates a virtual grounding wire management scenario based on the extracted features, including the grounding wire location, usage status, potential risk information and evaluation information of the temporary grounding wire positioning management model; using a variational autoencoder, through a comparative learning method, the consistency between the generated scenario and the actual situation is improved; the deep neural network model is trained to optimize the generated virtual scene.

[0018] As a preferred solution of the temporary grounding wire positioning management method based on remote radio frequency technology of the present invention, wherein: the encoder includes a 1D convolution layer, a 2D convolution layer, a first LSTM layer and an attention mechanism; the decoder includes a deconvolution layer, a second LSTM layer and a multi-head self-attention layer.

[0019] As a preferred solution of the temporary grounding wire positioning management method based on remote radio frequency technology of the present invention, wherein: training the deep neural network model includes preprocessing historical data and real-time data; dividing the preprocessed historical data and real-time data into a training set, a validation set and a test set; using the Adam optimizer to train the deep neural network model, using reconstruction loss and KL divergence as the objective function of the variational autoencoder; using the contrastive learning loss function to enhance the authenticity of the generated scene; using the validation set to evaluate the model and adjust the hyperparameters, and using the early stopping method to prevent overfitting; evaluating the performance of the adjusted deep neural network model on the test set to complete the training of the deep neural network model.

[0020] As a preferred solution of the temporary grounding wire positioning management method based on remote radio frequency technology of the present invention, wherein: combining the temporary grounding wire intelligent management model and the virtual grounding wire management scene, the temporary grounding wire use warning and management include: when M(x, y, t) < the first threshold, it is judged as a normal state, and the grounding wire position, usage status and prediction information are displayed in real time through the monitoring software, and marked as a green safety area in the virtual scene; when the first threshold ≤ M(x, y, t) ≤ the second threshold, it is judged as an attention state, and an early warning message is sent to the management personnel, and the relevant area is marked as a yellow warning area in the virtual scene, and a potential risk analysis report is generated; when M(x, y, t) > the second threshold, it is judged as a warning state, and the relevant personnel are immediately notified to conduct on-site inspections, and the emergency plan is activated. The relevant area is marked as a red danger area in the virtual scene, and possible fault development situations are simulated to provide support for emergency decision-making.

[0021] Another object of the present invention is to provide a temporary grounding wire positioning system based on remote radio frequency technology, including: a model construction module, used to collect temporary grounding wire related data and construct a temporary grounding wire positioning management model; a scenario construction module, used to construct a deep neural network model and generate a virtual grounding wire management scenario; an early warning management module, used to combine the temporary grounding wire intelligent management model and the virtual grounding wire management scenario to perform temporary grounding wire usage early warning and management.

[0022] A computer device includes a memory and a processor, wherein the memory stores a computer program, and is characterized in that when the processor executes the computer program, the steps of the temporary grounding wire positioning management method based on remote radio frequency technology are implemented as described above.

[0023] A computer-readable storage medium having a computer program stored thereon, characterized in that when the computer program is executed by a processor, the steps of the temporary grounding wire positioning management method based on remote radio frequency technology are implemented as described above.

[0024] The beneficial effects of the present invention are as follows: intelligent, precise and visual grounding line management is achieved through multiple innovative steps. By collecting multi-dimensional data and constructing complex mathematical models, a comprehensive quantitative evaluation of the grounding line status is achieved, and the management accuracy and reliability are improved. The virtual management scene is generated by deep neural networks, which enhances the insight of managers. Combining intelligent management models and virtual scenes, a multi-level early warning and management system is established to effectively reduce safety hazards. Advanced machine learning algorithms are used to process data to improve the depth and breadth of analysis. The authenticity of virtual scenes is ensured by variational autoencoders and contrastive learning. Finally, a hierarchical management strategy is adopted to take corresponding measures according to different risk levels to maximize the safe operation of the power system. This method not only improves management efficiency and reduces human errors, but also significantly enhances the safety and reliability of the power system, making an important contribution to the development of smart grids. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0026] Figure 1 This is a schematic diagram of the structure of a terminal in the first embodiment of the present invention;

[0027] Figure 2 It is a schematic diagram of a flow chart in the first embodiment of the present invention;

[0028] Figure 3 FIG. 4 is a schematic diagram of the structure of a computer device in a third embodiment of the present invention. DETAILED DESCRIPTION

[0029] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0030] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0031] Example 1

[0032] Reference Figure 1 , as an embodiment of the present invention, provides a temporary grounding wire positioning management method based on remote radio frequency technology.

[0033] First, the temporary grounding wire positioning management method based on remote radio frequency technology provided by this application can be applied to Figure 1 In the terminal shown. Figure 1 As shown, the terminal may include one or two ( Figure 1 Only one is shown in the figure) processor and memory for storing data, wherein the processor may include but is not limited to a processing system such as a microprocessor MCU or a programmable logic device FPGA. The above terminal may also include a transmission device and an input and output device for communication functions. It can be understood by ordinary technicians in this field that Figure 1 The structure shown is only for illustration and does not limit the structure of the above terminal. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations shown.

[0034] The memory can be used to store computer programs, such as the computer program corresponding to the temporary grounding line positioning management method based on remote radio frequency technology in the present embodiment. The processor executes various functional applications and data processing by running the computer program stored in the memory, that is, implementing the above method. The memory may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage systems, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include a memory remotely arranged relative to the processor, and these remote memories may be connected to the terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0035] The transmission device is used to receive or send data via a network. The above network includes a wireless network provided by a communication provider of the terminal. In one example, the transmission device includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device can be a radio frequency (Radio Frequency, referred to as RF) module, which is used to communicate with the Internet wirelessly.

[0036] like Figure 2 As shown, the embodiment of the present invention provides a temporary grounding wire positioning management method based on remote radio frequency technology, and the method is applied to Figure 1 The terminal in is used as an example to illustrate, including the following steps:

[0037] S1: Collect data related to temporary grounding wires and build a temporary grounding wire positioning management model.

[0038] Specifically, the data related to temporary grounding lines include real-time data and historical data. Real-time data includes radio frequency identification data, environmental data, location data, usage status data, and locking accessory status data; historical data includes power plant layout data, historical usage frequency data, and usage time fluctuation data.

[0039] Furthermore, constructing a temporary grounding wire location management model includes calculating a comprehensive evaluation factor based on radio frequency identification data, environmental data, usage status data, and locking accessory status. The calculation formula of the comprehensive evaluation factor is as follows:

[0040]

[0041] Among them, F(t) is a comprehensive evaluation factor, which represents the comprehensive performance status of the grounding wire at time t; S(τ) represents the RF signal strength, which represents the position and connection status of the grounding wire; E(τ) represents the environmental factor, which represents the impact of environmental conditions such as temperature and humidity on the grounding wire; U(τ) represents the usage status of the grounding wire, which represents the usage frequency and load of the grounding wire; C(τ) represents the locking accessory status, which represents the safety and stability status of the grounding wire; τ represents the integral variable; w1, w2 and w3 are all weight coefficients, which are used to adjust the relative importance of RF signal strength and environmental factors, adjust the relative importance of grounding wire usage status, and adjust the relative importance of locking accessory status, respectively; α represents the environmental impact adjustment parameter, which adjusts the impact of environmental factors; λ1 is a power adjustment function, which adjusts the nonlinear impact of RF signal strength; log(.) is used to smooth the impact of locking accessory status.

[0042] Preferably, the comprehensive evaluation factor comprehensively considers multiple factors such as RF signal strength, environmental factors, usage status, locking accessory status, etc., and can comprehensively evaluate the comprehensive performance status of the grounding wire. The influence of each factor can be adjusted according to actual needs through the weight coefficient. The environmental impact adjustment parameter is introduced so that the evaluation result can dynamically adapt to different environmental conditions.

[0043] Furthermore, the spatial distribution factor is calculated by combining the layout complexity and the spatial distance. The calculation formula of the spatial distribution factor is as follows:

[0044]

[0045] Among them, D(x,y) is the spatial distribution factor, which represents the spatial distribution influence of the grounding wire at the position (x,y), (x,y) represents the coordinates of the grounding wire position to be calculated, L(.) represents the layout complexity, which represents the layout complexity of the power plant at the point (ξ,η); ξ and η are both integral variables, representing the coordinates of any point in the power plant; A represents the entire power plant area, and ∈ represents a small constant.

[0046] Preferably, the layout complexity is introduced into the formula, which can reflect the complexity of different areas inside the power plant, take into account the spatial distribution of grounding wires at different positions, and improve the accuracy of spatial distribution by integrating the influence of distances between different positions. This formula can be applied to the layouts of different power plants and different grounding wire installation locations.

[0047] Furthermore, through time series analysis, historical data is converted into usage pattern factors. The calculation formula of usage pattern factors is as follows:

[0048] P(t)=β1·ARIMA(H(t))+β2·GARCH(V(t))

[0049] Among them, P(t) represents the usage mode factor, which indicates the usage mode status of the grounding wire at time t, H(t) represents the historical usage frequency of the grounding wire, which indicates the usage frequency of the grounding wire in the past period of time, V(t) represents the volatility of the usage time of the grounding wire, which indicates the volatility of the usage time of the grounding wire, ARIMA(.) represents the autoregressive integrated moving average model, which is used to predict the historical usage frequency of the time series; GARCH(.) represents the generalized autoregressive conditional heteroskedasticity model, which is used to predict the volatility of the usage time of the time series; β1 and β2 are both weight coefficients, which are used to adjust the importance of the ARIMA model and the weight of the GARCH model respectively;

[0050] Preferably, the ARIMA and GARCH models are used to perform time series analysis on historical data, which can accurately predict the volatility of usage frequency and usage duration, adjust the influence of the two models through weight coefficients, and flexibly adapt to different usage situations.

[0051] Furthermore, by weighted combination of comprehensive evaluation factors, spatial distribution factors and usage pattern factors, a temporary grounding wire location management model is obtained. The calculation formula of the temporary grounding wire location management model is as follows:

[0052]

[0053] Among them, M(x, y, t) is the evaluation value of the temporary grounding wire positioning management model, which represents the comprehensive evaluation status of the grounding wire at time t and position (x, y); γ1, γ2 and γ3 are all weight coefficients, γ1 is used to adjust the relative importance of the comprehensive evaluation factor F(t) and the spatial distribution factor D(x, y), γ2 is used to adjust the relative importance of the usage mode factor P(t), and γ3 is used to adjust the change rate of the comprehensive evaluation factor The relative importance of It represents the rate of change of the comprehensive evaluation factor, and it represents the change of the comprehensive evaluation factor F(t) over time.

[0054] Preferably, the formula combines comprehensive evaluation factors, spatial distribution factors and usage mode factors to comprehensively evaluate the comprehensive status of the grounding wire. The change rate of the comprehensive evaluation factors is introduced, which can reflect the changes in the status of the grounding wire in real time and provide more accurate management and early warning. Through the weight coefficient, the influence of each factor can be flexibly adjusted to meet different management needs. The formula combines multiple complex factors and improves the accuracy and reliability of the model through weighted combination. It can provide scientific decision support, and can make status judgments (normal, attention, warning) according to different evaluation value ranges, provide timely early warning information and management measures, and ensure the safe operation of the grounding wire. The temporary grounding wire positioning management model has comprehensiveness and dynamic adjustment capabilities, and is particularly suitable for complex practical application scenarios.

[0055] S2: Build a deep neural network model to generate virtual ground line management scenarios.

[0056] Specifically, a deep neural network model is constructed, including an encoder and a decoder; the encoder is responsible for feature extraction, and the decoder is responsible for scene generation.

[0057] Preferably, a latent space is added between the encoder and the decoder to represent the compressed features.

[0058] Furthermore, the encoder receives real-time data, historical records, and the evaluation value of the temporary grounding wire positioning management model as input, and extracts features through multi-layer convolution and recurrent neural networks; the input layer of the encoder receives real-time data (such as radio frequency identification data, environmental data, etc.) and historical records (such as frequency of use, duration, etc.), the convolution layer uses 1D convolution to process time series data, and 2D convolution to process spatially related data; the recurrent neural network layer uses the first LSTM layer to capture the temporal dependency of the data, and introduces a self-attention layer to highlight important features.

[0059] Preferably, by using the convolutional layer and the first LSTM layer in the encoder, the deep neural network model can extract complex spatiotemporal features from real-time data and historical records, so that the model can capture subtle patterns and long-term dependencies in ground line use and management. Using the attention mechanism in the encoder and decoder can help the model focus on the most important information and improve the effect of feature extraction and generation.

[0060] Furthermore, the decoder generates a virtual grounding wire management scenario based on the extracted features, including the grounding wire location, usage status, potential risk information, and evaluation information of the temporary grounding wire positioning management model; the input layer is used to receive the compressed features from the encoder and gradually restore the spatial information through the deconvolution layer; the second LSTM layer generates time-related scene information; the output layer generates a virtual scene, including the grounding wire location, usage status, and potential risk information.

[0061] Preferably, the decoder is designed so that the model can generate a detailed virtual ground wire management scenario, including ground wire location, usage status and potential risk information. This provides managers with a comprehensive overview of the situation.

[0062] Furthermore, a variational autoencoder is used to add two fully connected layers to the encoder output, outputting the mean and variance respectively. The reparameterization technique is used to sample from the normal distribution to generate a latent vector, which the decoder uses to reconstruct the input data.

[0063] Furthermore, the characteristics include time series characteristics, spatial distribution characteristics, state transition characteristics, environment-related characteristics and abnormal pattern characteristics; time series characteristics include the periodic patterns of grounding wire usage frequency and usage duration; spatial distribution characteristics include the location distribution pattern of grounding wires in the power plant; state transition characteristics include the regularity of grounding wires switching from one state to another; environment-related characteristics include the association between environmental factors (such as temperature and humidity) and grounding wire usage; abnormal pattern characteristics include abnormal events and failure modes in historical records.

[0064] Furthermore, through contrastive learning methods, an enhanced version is created for each input data (such as adding noise, rotation, etc.), and a contrastive loss function is used to maximally increase the similarity between different enhanced versions of the same data, while reducing the similarity between different data. This helps the model learn more robust feature representations and improve the realism of the generated scenes.

[0065] Furthermore, the process of training a deep neural network model includes preprocessing historical and real-time data; cleaning historical and real-time data, removing outliers and duplicate data, standardizing input data, scaling data to the same range using Z-score or Min-Max methods, handling missing values, and selecting appropriate methods based on data characteristics (such as mean filling, median filling, or advanced interpolation methods)

[0066] Furthermore, the preprocessed historical data and real-time data are divided into a training set (70%), a validation set (15%), and a test set (15%) to ensure that the data set division maintains temporal continuity and avoids data leakage;

[0067] Furthermore, the Adam optimizer is used to train the deep neural network model, the appropriate learning rate and decay strategy are set, the reconstruction loss (such as mean square error or cross entropy) and KL divergence are used as the objective function of the variational autoencoder, and the L1 / L2 regularization terms are introduced to control the model complexity and prevent overfitting.

[0068] Furthermore, a contrastive learning loss function (such as NT-Xent loss) is used to enhance the realism of the generated scenes, and the temperature parameters of contrastive learning are adjusted to balance the influence of positive and negative samples.

[0069] Furthermore, the validation set is used for model evaluation, key indicators such as reconstruction error, KL divergence and contrast loss are monitored, hyperparameters are adjusted using methods such as grid search or Bayesian optimization, and early stopping is used to prevent overfitting.

[0070] Evaluate the performance of the tuned deep neural network model on the test set and calculate multiple evaluation metrics such as mean squared error (MSE), mean absolute error (MAE), and R 2 scores, etc., perform error analysis, identify the strengths and limitations of the model, explain model predictions using techniques such as SHAP values ​​or LIME, analyze feature importance, understand the impact of different inputs on model output, compress and quantize the final model, and perform version control.

[0071] Preferably, once training is completed, the deep neural network model can quickly process real-time data, automatically generate the latest virtual management scenarios, and reduce human intervention, which can not only improve management efficiency but also enhance security.

[0072] S3: Combine the temporary grounding wire intelligent management model and virtual grounding wire management scenario to perform temporary grounding wire usage warning and management.

[0073] Combined with the temporary grounding wire intelligent management model and virtual grounding wire management scenario, the temporary grounding wire usage warning and management include:

[0074] When M(x, y, t) is less than the first threshold of 0.6, it is judged as a normal state, and the grounding wire position, usage status and prediction information are displayed in real time through the monitoring software, and marked as a green safety area in the virtual scene;

[0075] When the first threshold value 0.6≤M(x,y,t)≤the second threshold value 0.8, it is judged as a caution state, an early warning message is sent to the management personnel, the relevant area is marked as a yellow warning area in the virtual scene, and a potential risk analysis report is generated;

[0076] When M(x, y, t)>the second threshold value of 0.8, it is judged as a warning state, and relevant personnel are immediately notified to conduct on-site inspections, activate the emergency plan, mark the relevant areas as red danger areas in the virtual scene, and simulate possible fault development situations to provide support for emergency decision-making.

[0077] Preferably, by setting different thresholds, the use status of the grounding wire is divided into three levels: normal, attention and warning. This hierarchical management method can more accurately reflect the actual situation and help to reasonably allocate resources; use color coding (green, yellow, red) to mark areas of different states in the virtual scene. This intuitive visualization method can help managers quickly identify problem areas and improve management efficiency; the monitoring software displays the grounding wire position, use status, prediction information and evaluation information of the temporary grounding wire positioning management model in real time to ensure that managers can grasp the latest situation in a timely manner and respond quickly to possible problems; send warning information to managers in the attention state. This active warning mechanism can help managers take preventive measures before the problem worsens; combine the temporary grounding wire intelligent management model and the virtual grounding wire management scene to realize the intelligence and automation of the management process and reduce the possibility of human error; not only monitor the location of the grounding wire, but also include the use status, prediction information and evaluation information of the temporary grounding wire positioning management model, providing comprehensive safety management; combine the temporary grounding wire positioning management model with the virtual grounding wire management scene, which not only takes advantage of data analysis, but also provides an intuitive visualization interface, achieving the effect of 1+1>2.

[0078] Example 2

[0079] Reference Figure 1-2 , as an embodiment of the present invention, provides a temporary ground wire positioning system based on remote radio frequency technology, comprising:

[0080] For the specific limitations of the temporary grounding wire locating system based on remote radio frequency technology, please refer to the limitations of the temporary grounding wire locating management method based on remote radio frequency technology above, which will not be repeated here. Each module in the above-mentioned temporary grounding wire locating system based on remote radio frequency technology can be implemented in whole or in part through software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0081] Example 3

[0082] Reference Figure 3 , which is the third embodiment of the present invention. Based on the first two embodiments, the embodiment of the present invention provides a computer device, which may be a server, and its internal structure diagram may be as shown in FIG. Figure 3 As shown. The computer device includes a processor, a memory and a network interface connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium.

[0083] The database of the computer device is used to store action detection data. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, the steps in any of the above-mentioned sparse tensor operation acceleration method embodiments are implemented.

[0084] Those skilled in the art will understand that Figure 3 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0085] In one embodiment, an embodiment of the present invention provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps in any of the above-mentioned sparse tensor operation acceleration method embodiments are implemented.

[0086] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory or optical memory, etc. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0087] Example 4

[0088] As an embodiment of the present invention, a temporary grounding wire positioning management method based on remote radio frequency technology is provided. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through simulation experiments.

[0089] Specifically, in a high-voltage distribution room of a power plant, a six-month experiment was conducted to verify the effectiveness of a temporary grounding wire location management method based on remote radio frequency technology. First, micro RFID tags and sensors were installed on all temporary grounding wires to collect real-time data. At the same time, environmental sensors and RFID readers were installed at key locations in the distribution room to obtain environmental data and grounding wire location information.

[0090] Furthermore, before the experiment started, historical data from the past three years were collected, including power plant layout data, grounding wire usage frequency and usage duration fluctuation data. During actual operation, the system collected real-time data every 5 minutes, including radio frequency identification data, environmental data, location data, usage status data, and locking accessory status data. These data were input into the trained deep neural network model to generate a virtual grounding wire management scenario.

[0091] Furthermore, in order to evaluate the effectiveness of this method, seven temporary grounding wires were selected for monitoring for six months and compared with the traditional manual inspection method. The following table shows the experimental results:

[0092] Table 1 Comparison results between the temporary grounding wire positioning management method based on remote radio frequency technology and the traditional manual inspection method

[0093]

[0094] Furthermore, by analyzing the data in Table 1, it can be clearly seen that our solution has significant advantages over the traditional manual inspection method.

[0095] Furthermore, in terms of abnormal detection rate, our solution reached an average of 98.4%, while the traditional method was only 85.2%. This means that our solution can more comprehensively discover potential safety hazards and greatly improve the safety of power plants. At the same time, the false alarm rate of our solution was significantly reduced, averaging only 2.1%, while the traditional method was as high as 7.5%. This not only reduces unnecessary waste of human resources, but also improves the credibility of management.

[0096] Furthermore, in terms of response time, our solution only takes an average of 3.2 minutes to detect anomalies and respond, while the traditional method takes 45.6 minutes. This nearly 15-fold time difference can have a decisive impact when dealing with emergencies, greatly improving the emergency response capabilities of power plants.

[0097] Furthermore, positioning accuracy is also a major improvement of our solution, with an average positioning accuracy of 0.79 meters, a qualitative leap compared to the 3.5 meters of the traditional method. This high-precision positioning capability allows maintenance personnel to quickly and accurately find the problem, greatly improving maintenance efficiency.

[0098] Furthermore, the improvement in early warning accuracy is also significant, with our solution reaching an average of 96.6%, while the traditional method is only 82.3%. This means that the new method can more accurately predict potential risks, allowing managers to take more proactive and effective preventive measures.

[0099] Furthermore, our solution has improved management efficiency by an average of 35.1%. This efficiency improvement is not only reflected in the savings in time and human resources, but also in the accuracy and timeliness of decision-making. By generating virtual ground line management scenarios, managers can more intuitively understand the operation status of the entire system and make more informed decisions.

[0100] Finally, from the perspective of economic benefits, our solution can save an average of RMB 125,000 per grounding wire per year. These savings come from reduced manual inspection time, reduced equipment failure rate, and improved energy efficiency.

[0101] In summary, our solution has shown significant advantages in many aspects such as anomaly detection, response speed, positioning accuracy, warning accuracy, management efficiency and economic benefits. It not only improves the safety and reliability of power plants, but also realizes real-time monitoring and prediction of complex systems through the combination of deep neural network models and virtual scenes.

[0102] 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 preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A temporary grounding wire positioning management method based on remote radio frequency technology, characterized in that: include: Collect data related to temporary grounding wires and build a temporary grounding wire positioning management model; Build a deep neural network model to generate virtual ground line management scenarios; In combination with the temporary grounding wire intelligent management model and the virtual grounding wire management scenario, early warning and management of temporary grounding wire use are performed.

2. The temporary grounding wire positioning management method based on remote radio frequency technology according to claim 1 is characterized in that: The temporary grounding wire related data includes real-time data and historical data. The real-time data includes radio frequency identification data, environmental data, location data, usage status data and locking accessory status data; the historical data includes power plant layout data, historical usage frequency data and usage time fluctuation data.

3. The temporary grounding wire positioning management method based on remote radio frequency technology as claimed in claim 2 is characterized in that: The construction of the temporary grounding line positioning management model includes: A comprehensive evaluation factor is calculated based on the RFID data, the environmental data, the usage status data, and the locking accessory status. The calculation formula of the comprehensive evaluation factor is as follows: Among them, F(t) is the comprehensive evaluation factor, which represents the comprehensive performance status of the grounding wire at time t, S(τ) represents the RF signal strength, E(τ) represents the environmental factor, U(τ) represents the use status of the grounding wire, C(τ) represents the state of the locking accessory, τ represents the integral variable, w1, w2 and w3 are all weight coefficients, α represents the environmental impact adjustment parameter, and λ1 is the power adjustment function; The spatial distribution factor is calculated by combining the layout complexity and the spatial distance. The calculation formula of the spatial distribution factor is as follows: Where D(x,y) is the spatial distribution factor, which represents the spatial distribution effect of the grounding wire at the position (x,y); L(.) represents the layout complexity, which represents the layout complexity of the power plant at the point (ξ,η); ξ and η are both integral variables, which represent the coordinates of any point in the power plant; A represents the entire power plant area, and ∈ represents a small constant; Through time series analysis, historical data is converted into usage pattern factors. The calculation formula of usage pattern factors is as follows: P(t)=β1·ARIMA(H(t))+β2·GARCH(V(t)) Among them, P(t) represents the usage pattern factor, which indicates the usage pattern status of the grounding wire at time t, H(t) represents the historical usage frequency of the grounding wire, V(t) represents the volatility of the usage duration of the grounding wire, ARIMA(.) represents the autoregressive integrated moving average model, which is used to predict the historical usage frequency of the time series; GARCH(.) represents the generalized autoregressive conditional heteroskedasticity model, which is used to predict the volatility of the usage duration of the time series; β1 and β2 both represent weight coefficients, which are used to adjust the importance of the ARIMA model and the weight of the GARCH model respectively; By weighted combination of comprehensive evaluation factors, spatial distribution factors and usage mode factors, a temporary grounding wire location management model is obtained. The calculation formula of the temporary grounding wire location management model is as follows: Wherein, M(x, y, t) is the evaluation value of the temporary grounding wire location management model, which represents the comprehensive evaluation status of the grounding wire at time t and position (x, y); γ1, γ2 and γ3 are all weight coefficients. Represents the rate of change of the comprehensive evaluation factor.

4. The temporary grounding wire positioning management method based on remote radio frequency technology as claimed in claim 3 is characterized in that: The generating of the virtual ground line management scenario includes: Build a deep neural network model, including encoder and decoder; The encoder receives real-time data, historical records, and the evaluation value of the temporary grounding wire location management model as input, and extracts features through multi-layer convolution and recurrent neural networks; Based on the extracted features, the decoder generates a virtual grounding wire management scenario, including the grounding wire location, usage status, potential risk information, and evaluation information of the temporary grounding wire location management model; Using variational autoencoders, we can improve the consistency between generated scenes and real situations through contrastive learning methods. Train deep neural network models to optimize the generated virtual scenes.

5. The temporary grounding wire positioning management method based on remote radio frequency technology as claimed in claim 4 is characterized in that: The encoder includes a 1D convolution layer, a 2D convolution layer, a first LSTM layer and an attention mechanism; the decoder includes a deconvolution layer, a second LSTM layer and a multi-head self-attention layer.

6. The temporary grounding wire positioning management method based on remote radio frequency technology as claimed in claim 5 is characterized in that: The training deep neural network model includes: Preprocess historical data and real-time data; Divide the preprocessed historical data and real-time data into training set, validation set and test set; The Adam optimizer is used to train the deep neural network model, and the reconstruction loss and KL divergence are used as the objective function of the variational autoencoder. Use contrastive learning loss function to enhance the realism of generated scenes; Use the validation set for model evaluation and hyperparameter adjustment, and use early stopping to prevent overfitting; Evaluate the performance of the adjusted deep neural network model on the test set and complete the training of the deep neural network model.

7. The temporary grounding wire positioning management method based on remote radio frequency technology according to claim 6 is characterized in that: The combination of the temporary grounding wire intelligent management model and the virtual grounding wire management scenario to perform temporary grounding wire usage warning and management includes: When M(x, y, t) < the first threshold, it is judged as a normal state, and the grounding wire position, usage status and prediction information are displayed in real time through the monitoring software, and marked as a green safety area in the virtual scene; When the first threshold ≤ M(x, y, t) ≤ the second threshold, it is judged as a caution state, an early warning message is sent to the management personnel, the relevant area is marked as a yellow warning area in the virtual scene, and a potential risk analysis report is generated; When M(x, y, t)>the second threshold, it is judged as a warning state, and relevant personnel are immediately notified to conduct on-site inspections, activate the emergency plan, mark the relevant areas as red danger areas in the virtual scene, and simulate possible fault development situations to provide support for emergency decision-making.

8. A temporary grounding wire positioning management system based on remote radio frequency technology according to any one of claims 1 to 7, characterized in that: include: Model building module, used to collect temporary grounding wire related data and build a temporary grounding wire positioning management model; A scenario building module, which is used to build a deep neural network model and generate virtual ground wire management scenarios; The early warning management module is used to combine the temporary grounding wire intelligent management model and the virtual grounding wire management scenario to perform early warning and management of temporary grounding wire use.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the temporary grounding wire positioning management method based on remote radio frequency technology described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the temporary grounding wire positioning management method based on remote radio frequency technology described in any one of claims 1 to 7 are implemented.

Images