Intelligent induction type cable quick connector plugging method

Abstract

The present disclosure relates to an intelligent induction type cable quick connector plugging method, comprising: removing noise and errors in dust particle data through a signal processing module, combining the processed dust particle data with ambient air pressure data, using a Kalman filter algorithm to construct a first data set, and storing the data in a predefined format; obtaining the output results of a particle swarm optimization model, analyzing the movement trend and concentration change of dust, monitoring the insulation state of the cable joint in real time through an insulation state sensor of a dust removal instrument, and constructing a second data set based on the movement trend, concentration change of dust particles and the insulation state of the cable joint; obtaining the working intensity of the dust removal instrument through a fuzzy logic controller in the dust removal instrument; judging whether the insulation performance of the cable joint meets the safety standard based on the insulation state of the cable joint; collecting real-time plugging data during the plugging process, and evaluating the accuracy and safety of the plugging operation by analyzing the real-time plugging data.

Description

Technical Field

[0001] The present disclosure relates to the technical field of cable connector plugging, and in particular to a plugging method for an intelligent inductive cable quick connector. Background Art

[0002] One of the main technical challenges in plugging in high-voltage cable quick connectors is the impact of dust particles. Dust particles easily adhere to the insulating surface of the cable connector, severely impacting the connector's insulation performance and potentially leading to safety issues such as insulation breakdown. Ensuring that the connector's insulating surface remains clean before and after plugging in is crucial. Dust removal also requires an efficient dust removal system. This system should be able to automatically adjust the frequency and intensity of dust removal based on monitored dust movement data to ensure that the cable connector plugging process is unaffected by dust. Due to the complex environment and varying dust particle sizes, the dust removal system must adapt to different situations and remove various dust particles in real time. The main technical challenge lies in accurately and in real time monitoring the dynamic changes in dust and, based on the monitoring data, efficiently removing dust particles to ensure the safe and reliable plugging in of high-voltage cable quick connectors. Summary of the Invention

[0003] In order to solve the problems existing in the above-mentioned prior art, the present disclosure aims to provide an intelligent inductive cable quick connector plugging method to ensure safe and reliable plugging of high-voltage cable quick connectors.

[0004] The present invention discloses a method for plugging a smart inductive cable quick connector, comprising the following steps:

[0005] The system uses environmental sensors to detect dust particle data in the air in real time, record the size and concentration of dust particles, and transmit the collected dust particle data to a cloud server via a wireless network. The environmental sensors include optical particle counters, laser radars, and cameras. The cameras are used to capture the movement path and speed of dust particles. The air pressure monitoring system detects ambient air pressure data in real time and transmits it to the cloud server.

[0006] Removing noise and errors from the dust particle data through a cloud server to obtain processed dust particle data, combining the processed dust particle data with ambient air pressure data, obtaining a first data set through a Kalman filter algorithm, and storing the first data set in a predefined format;

[0007] Initial parameters of a particle swarm optimization model are set via a cloud server, and the first data set is input into the particle swarm optimization model to train the particle swarm optimization model; the initial parameters include the number, velocity, and position of particles; and the particle swarm optimization model is used to generate a prediction result including a motion trend of dust particles;

[0008] The output results of the particle swarm optimization model are obtained through the dust removal instrument's built-in system, and the movement trend and concentration changes of the dust particles are analyzed. The insulation status of the cable connector is obtained through the dust removal instrument's insulation status sensor. A second data set is constructed by combining the movement trend of the dust particles, the concentration changes, and the insulation status of the cable connector. The second data set is used to adjust the operating frequency and cleaning intensity of the dust removal instrument.

[0009] The working intensity of the dust removal instrument is obtained through a fuzzy logic controller in the dust removal instrument; the input parameters of the fuzzy logic controller include dust movement trend, concentration change, and insulation status of cable connectors, and the output parameter is the working intensity of the dust removal instrument; the working intensity of the dust removal instrument includes voltage, current, operating frequency, vibration frequency, and wind speed;

[0010] Based on the insulation state of the cable joint, it is determined whether the insulation performance of the cable joint meets the safety standard. If the insulation performance of the cable joint meets the safety standard, an instruction to perform a plugging operation on the cable joint is issued. If the insulation performance of the cable joint does not meet the safety standard, a second data set is input into a fuzzy logic controller to obtain output parameters and issue an instruction to cause a dust removal device to perform a dust removal operation according to the output parameters of the fuzzy logic controller. By analyzing the insulation state of the cable joint during dust removal, instructions to cause the dust removal device to perform a dust removal operation according to the output parameters of the fuzzy logic controller are continuously issued until the insulation performance of the cable joint meets the safety standard.

[0011] By continuously monitoring the communication status between the cloud server, cable connector and dust removal instrument, the stability of data transmission is ensured and real-time plugging data during the plugging process is collected; the real-time plugging data is analyzed by the cloud server application data acquisition module to evaluate the accuracy and safety of the plugging operation; the real-time plugging data includes torque, insertion force and dust concentration.

[0012] Preferably, the method of detecting dust particle data in the air in real time by using an environmental sensor, recording the size and concentration of the dust particles, and transmitting the collected dust particle data to a cloud server via a wireless network; the environmental sensor includes an optical particle counter, a laser radar, and a camera device; the camera device is used to capture the movement path and speed of dust particles; and the method of detecting ambient air pressure data in real time by using an air pressure monitoring system and transmitting the data to the cloud server includes:

[0013] An optical particle counter is used to detect dust particles in the air in real time to obtain information on particle size and concentration; a laser radar is used to capture the movement path and speed of particles; and a camera is used to record visual image data of particles.

[0014] The detected dust particle size, concentration, movement path and speed as well as visual image data are transmitted in real time via wireless network to the cloud server for summary processing;

[0015] The detected dust particle size, concentration, movement path and movement speed, as well as visual image data are cleaned and standardized by a data preprocessing method of data cleaning and normalization, and a dust particle data model is established by a support vector machine (SVM) and a random forest algorithm;

[0016] Based on the established dust particle data model, through time series analysis and regression analysis prediction methods, the changing trend of dust particle concentration in the air over a period of time in the future is predicted in real time, and the changing trend of air quality is judged;

[0017] The air pressure monitoring system detects ambient air pressure data in real time and transmits the data to the cloud server;

[0018] The cloud server correlates and analyzes air pressure data with dust particle data to establish a prediction model between ambient meteorological conditions and air quality;

[0019] Estimate the air quality change trend in the future through meteorological forecast data.

[0020] Preferably, the method of removing noise and errors from the dust particle data through a cloud server to obtain processed dust particle data, combining the processed dust particle data with ambient pressure data, obtaining a first data set through a Kalman filter algorithm, and storing the first data set in a predefined format includes:

[0021] The high-frequency noise and random errors in the data are removed by wavelet threshold denoising method;

[0022] The signal processing module extracts features from the filtered dust particle data to obtain key feature parameters, including the concentration, particle size distribution, and movement speed of the dust particles;

[0023] Real-time air pressure data is acquired through an ambient air pressure monitoring system, and the air pressure data is time-synchronized and aligned with the processed dust particle data to obtain synchronized dust particle data and air pressure data;

[0024] fusing the synchronized dust particle data and air pressure data using a Kalman filter algorithm to obtain a first data set;

[0025] The first data set includes the concentration, particle size distribution and movement speed of dust particles and ambient air pressure data;

[0026] Organizing and packaging the first data set through a predefined data format and structure, and adding metadata and timestamp information;

[0027] The first data set is stored in a document-type NoSQL database such as MongoDB.

[0028] Preferably, the initial parameters of the particle swarm optimization model are set by a cloud server, and the first data set is input into the particle swarm optimization model to train the particle swarm optimization model; the initial parameters include the number, speed, and position of particles; the particle swarm optimization model is used to generate a prediction result including the movement trend of dust, including:

[0029] Selecting the number of particles based on the dimension, complexity, and computational resource factors of the first data set; and generating initial velocities and positions of the particles using a random function;

[0030] The particle swarm optimization model evaluates the optimization performance of each particle through a fitness function;

[0031] Setting a convergence condition, wherein the particle swarm optimization model iterates according to the convergence condition to obtain a prediction model for generating a prediction result including a motion trend of dust;

[0032] The convergence conditions include:

[0033] Set a maximum number of iterations. When the maximum number of iterations is reached, the particle swarm optimization model is considered to have converged.

[0034] Setting a minimum fitness threshold, when the optimal fitness value of multiple consecutive iterations changes less than the minimum fitness threshold, it is considered that the particle swarm optimization model has converged;

[0035] Setting a minimum particle position change threshold, when the particle position change of multiple consecutive iterations is less than the minimum particle position change threshold, the particle swarm optimization model is considered to have converged;

[0036] If the particle swarm optimization model satisfies one or more of the three convergence conditions, the particle swarm optimization model completes the iteration to obtain a prediction model for generating a prediction result including the movement trend of dust;

[0037] The prediction model is used to perform prediction analysis on the newly collected dust particle data to generate the dust movement trend in the future.

[0038] Preferably, the output results of the particle swarm optimization model are obtained through the built-in system of the dust removal instrument, and the movement trend and concentration change of the dust particles are analyzed; the insulation state of the cable joint is obtained through the insulation state sensor of the dust removal instrument; and a second data set is constructed by combining the movement trend of the dust particles, the concentration change, and the insulation state of the cable joint; the second data set is used to adjust the operating frequency and cleaning intensity of the dust removal instrument, including:

[0039] The output results of the particle swarm optimization model are obtained in real time via a wireless network; the position coordinates, movement speed and direction information of dust particles at different time points, and the numerical change curve of dust concentration are obtained;

[0040] Obtaining the motion data and concentration data of dust particles through analysis; correlating the motion data and concentration data of dust particles with the spatial position information of the dust removal instrument to determine the density and distribution of dust particles encountered by the dust removal instrument during future operation;

[0041] Obtaining an insulation resistance value threshold range and a dielectric loss factor threshold range, monitoring the insulation resistance value and dielectric loss factor at the cable joint in real time through the insulation status sensor of the dust removal instrument, and comparing the collected insulation resistance value with a preset insulation resistance value threshold range, and comparing the collected dielectric loss factor with a preset dielectric loss factor threshold range;

[0042] When the insulation resistance value exceeds the preset insulation resistance value threshold range, or when the dielectric loss factor exceeds the preset dielectric loss factor threshold range, it is determined that the insulation state is abnormal and a warning signal is triggered;

[0043] Correlating the abnormal insulation state data with the dust particle movement and concentration data at the corresponding time to construct a second data set;

[0044] Based on the AdaBoost algorithm, a correlation model between dust pollution and insulation abnormality was established. The probability distribution of insulation abnormality of cable joints under different dust particle concentrations and movement trends was obtained through the correlation model.

[0045] Adjust the operating frequency and cleaning intensity of dust removal equipment based on the predicted dust particle concentration and the probability of abnormal insulation status;

[0046] According to the model's predicted probability of insulation abnormality, the operating frequency and cleaning intensity of the dust removal equipment are divided into low, medium, and high levels. A probability threshold is preset for each level, namely the low probability threshold, the medium probability threshold, and the high probability threshold.

[0047] When the predicted dust particle concentration or insulation state abnormal probability exceeds the low-level probability threshold, the operating frequency and cleaning intensity of the dust removal equipment are increased;

[0048] When the predicted dust particle concentration and insulation state abnormal probability are lower than the low-level probability threshold, the operating frequency and cleaning intensity of the dust removal equipment are reduced;

[0049] According to the analysis results of the correlation model, the high-risk time window of abnormal insulation status of the cable joint is predicted. Before the high-risk time window, the cable joint is dusted and cleaned according to the operating frequency and cleaning intensity of the dust removal instrument corresponding to the probability threshold level of the high-risk time window.

[0050] Preferably, the working intensity of the dust removal instrument is obtained by a fuzzy logic controller in the dust removal instrument; the input parameters of the fuzzy logic controller include dust movement trend, concentration change and insulation state of the cable joint, and the output parameter is the working intensity of the dust removal instrument; the working intensity of the dust removal instrument includes voltage, current, operating frequency, vibration frequency and wind speed, including:

[0051] Obtain dust particle movement trends and concentration changes as well as cable joint insulation status;

[0052] The dust concentration is divided into: low dust concentration, medium dust concentration and high dust concentration;

[0053] The dust movement trend is divided into: steady dust movement trend, slowly rising dust movement trend and rapidly rising dust movement trend;

[0054] The cable joint insulation status is divided into: normal cable joint insulation status, slightly abnormal cable joint insulation status and seriously abnormal cable joint insulation status;

[0055] According to Mamdan i reasoning method, a fuzzy rule base is constructed;

[0056] Through the center of gravity defuzzification method, the result of fuzzy reasoning is converted into the specific working parameters of the dust removal instrument; and an instruction is issued to make the dust removal instrument work according to the specific working parameters.

[0057] Preferably, the method comprises: judging whether the insulation performance of the cable joint meets the safety standard based on the insulation state of the cable joint; issuing an instruction to perform a plugging operation on the cable joint if the insulation performance of the cable joint meets the safety standard; inputting the second data set into the fuzzy logic controller to obtain output parameters and issuing an instruction to cause the dust removal device to perform a dust removal operation according to the output parameters of the fuzzy logic controller if the insulation performance of the cable joint does not meet the safety standard; and continuously issuing instructions to cause the dust removal device to perform a dust removal operation according to the output parameters of the fuzzy logic controller by analyzing the insulation state of the cable joint during dust removal until the insulation performance of the cable joint meets the safety standard, comprising:

[0058] Preset the insulation status index threshold, collect the insulation resistance value and dielectric loss factor of the cable connector, and calculate the insulation status index IS:

[0059] IS=0.7×(R / R0)+0.3×(tanδ0 / tanδ),

[0060] Where R is the measured insulation resistance value, R0 is the insulation resistance threshold, tanδ is the measured dielectric loss factor, and tanδ0 is the dielectric loss factor threshold;

[0061] When IS is greater than or equal to the insulation state index threshold, it is determined that the insulation performance of the cable joint meets the safety standard; when IS is less than the insulation state index threshold, it is determined that the insulation performance of the cable joint does not meet the safety standard;

[0062] If the insulation performance of the cable connector meets the safety standard, an instruction to perform the plugging operation of the cable connector is issued;

[0063] If the insulation performance of the cable joint does not meet the safety standard, the second data set is input into the fuzzy logic controller;

[0064] According to Mamdan i reasoning method, a fuzzy rule base is constructed;

[0065] By using the center of gravity defuzzification method, the result of fuzzy reasoning is converted into the specific working parameters of the dust removal instrument; and an instruction is issued to make the dust removal instrument work according to the specific working parameters;

[0066] When the insulation state index IS is greater than the insulation state index threshold for multiple consecutive times, it is determined that the insulation performance of the cable joint has reached the safety standard, and an instruction to perform the plugging operation of the cable joint is issued;

[0067] Collect the insertion depth of the connector, the displacement and speed of the plugging mechanism, calculate the deviation between the actual insertion depth of the connector and the target depth, and adjust the movement of the plugging mechanism according to the deviation between the actual insertion depth and the target depth until the plugging operation of the cable connector is completed;

[0068] After completing the plugging operation of the cable connector, collect the axial compression force and judge whether the required tightening degree is achieved based on the axial compression force.

[0069] Preferably, the communication status between the cloud server, the cable connector and the dust removal instrument is continuously monitored to ensure the stability of data transmission and collect real-time plugging data during the plugging process; the real-time plugging data is analyzed by a data acquisition module on the cloud server to evaluate the accuracy and safety of the plugging operation; the real-time plugging data includes torque, insertion force and dust concentration, including:

[0070] Through the heartbeat mechanism, the communication status between the cloud server, cable connector and dust removal instrument is monitored and the round-trip delay is recorded;

[0071] The token bucket algorithm is used to shape and limit the data transmission traffic between the cloud server, cable connector and dust removal equipment; the token generation rate is dynamically adjusted according to the water level of tokens passing through;

[0072] When the water level of the token bucket exceeds a certain percentage for a period of time, a traffic anomaly alarm is triggered;

[0073] Collect the torque, insertion force and dust concentration in the plugging environment during the plugging process as real-time plugging data;

[0074] Pre-process the real-time plug-in data and compress the data through the run-length encoding algorithm;

[0075] The real-time plug-in data is filtered and smoothed by the Kalman filter algorithm to obtain the plug-in data;

[0076] Establishing a plugging operation evaluation model for judging the accuracy and safety of the current plugging operation through a decision tree algorithm, inputting the plugging data into the plugging operation evaluation model; judging the accuracy and safety of the current plugging operation;

[0077] The plugging data is collected and clustered. The elbow method is used to evaluate different clustering numbers K to obtain the optimal clustering number. The plugging data is classified using the K-means algorithm. The number, proportion and parameter distribution status of various plugging operations are counted to generate a plugging operation quality report.

[0078] The advantage of the intelligent induction cable quick connector plug-in method disclosed in the present invention is that the present invention solves the problem of the influence of dust particles on the insulation performance during the plug-in operation of high-voltage cable quick connectors in high-altitude areas. Due to the thin air at high altitudes, dust particles are easily suspended and adsorbed on the insulation surface of the cable connector, resulting in a decrease in insulation performance and even causing insulation breakdown. The present invention accurately monitors the dynamic changes of suspended dust through real-time monitoring and intelligent control systems, and automatically adjusts the dust removal frequency and intensity according to the monitoring data to ensure that the cable connector remains clean before and after plugging. The system can adapt to complex environments and different dust particle sizes, remove various dust particles in real time, and ensure the safe and reliable plugging of high-voltage cable connectors in extreme environments, solving the technical problem that traditional methods cannot effectively deal with dust problems in high-altitude areas. BRIEF DESCRIPTION OF THE DRAWINGS

[0079] Figure 1 The present invention provides a flow chart of a method for plugging in an intelligent inductive cable quick connector.

[0080] Figure 2The present invention is a schematic diagram of an intelligent inductive cable quick connector plugging method.

[0081] Figure 3 This is another schematic diagram of an intelligent inductive cable quick connector plugging method disclosed herein. DETAILED DESCRIPTION

[0082] like Figures 1 to 3 As shown, the intelligent inductive cable quick connector plugging method described in the present disclosure may specifically include:

[0083] Step S101: Using environmental sensors to detect dust particle data in the air in real time, record the size and concentration of the dust particles, and transmit the collected dust particle data to a cloud server via a wireless network. The environmental sensors include optical particle counters, laser radars, and cameras; the cameras are used to capture the movement path and speed of dust particles. A barometric pressure monitoring system detects ambient air pressure data in real time and transmits it to the cloud server.

[0084] Specifically, an optical particle counter is used to detect dust particle data in the air in real time to obtain information on particle size and concentration; a laser radar is used to capture the movement path and speed of particles; and a camera is used to record visual image data of particles.

[0085] The detected dust particle size, concentration, movement path and speed as well as visual image data are transmitted in real time via wireless network to the cloud server for summary processing;

[0086] The detected dust particle size, concentration, movement path and movement speed, as well as visual image data are cleaned and standardized by a data preprocessing method of data cleaning and normalization, and a dust particle data model is established by a support vector machine (SVM) and a random forest algorithm;

[0087] Based on the established dust particle data model, through time series analysis and regression analysis prediction methods, the changing trend of dust particle concentration in the air over a period of time in the future is predicted in real time, and the changing trend of air quality is judged;

[0088] The air pressure monitoring system detects ambient air pressure data in real time and transmits the data to the cloud server;

[0089] The cloud server correlates and analyzes air pressure data with dust particle data to establish a prediction model between ambient meteorological conditions and air quality;

[0090] Estimate the air quality change trend in the future through meteorological forecast data.

[0091] More specifically, the environmental sensors include optical particle counters, lidars, and cameras; the environmental sensors detect dust particle data in the air in real time, record the size and concentration of dust particles, and capture the movement path and speed of dust particles through cameras; the environmental sensors transmit the collected dust particle data to the cloud server via a wireless network; the air pressure monitoring system detects ambient air pressure data in real time and transmits it to the cloud server.

[0092] Environmental sensors use optical particle counters to detect dust particles in the air in real time, obtaining information on particle size and concentration. Meanwhile, lidar captures the particle path and velocity, and cameras record visual images of the particles. The environmental sensors transmit multi-dimensional data, including particle size, concentration, path, velocity, and visual images, to a cloud server via a wireless network for real-time aggregation and processing. After receiving the multi-dimensional dust particle data from the environmental sensors, the cloud server uses data cleaning and normalization preprocessing methods to clean and standardize the data. It then uses support vector machines (SVMs) and random forest algorithms to build a dust particle data model, exploring correlations and regularities within the data. The SVM algorithm effectively handles high-dimensional data and is suitable for classification with small sample sizes. The random forest algorithm handles nonlinear relationships and is less prone to overfitting. Based on the established dust particle data model, the cloud server uses time series analysis and regression analysis to predict future trends in dust particle concentration in the air, identify air quality trends, and provide data support for environmental management decisions. The air pressure monitoring system monitors ambient air pressure data in real time and transmits the data to the cloud server. Air pressure data is closely related to dust particle data, and changes in air pressure affect the movement and diffusion of dust particles. Incorporating air pressure data into analysis and prediction models can comprehensively characterize the changing patterns of air quality. The cloud server correlates and analyzes air pressure data with dust particle data, studying the impact of air pressure changes on dust particle movement and establishing a predictive model linking ambient meteorological conditions and air quality. Weather forecast data is used to estimate air quality trends over the coming period. Environmental sensors and air pressure monitoring systems continuously collect data and transmit it to the cloud server. The server uses gradient descent and cross-validation methods to self-optimize and iteratively update the prediction model, continuously improving the accuracy and reliability of air quality predictions. During the optimization process, the gradient descent method is used to find the optimal values ​​of the model parameters, and the cross-validation method is used to select the best combination of model parameters to avoid overfitting or underfitting of the model.

[0093] For example, the environmental sensor collects 100 air samples per second using an optical particle counter, counting particles with diameters of 0.5μm, 1.0μm, 2.5μm, and 5.0μm in each sample. Simultaneously, a lidar (lidar) scans the air for dust particles at a frequency of 10Hz, capturing their trajectory and instantaneous velocity. A camera records video images of dust particles at a resolution of 1920×1080 pixels at 30 frames per second. This multi-dimensional data is transmitted in real time to a cloud server via a Wi-Fi 6 network, with a transmission latency of less than 10ms and a data throughput of 1Gbps. The cloud server uses the Apache Spark big data processing framework to clean and normalize the received data, removing outliers and invalid values ​​and normalizing the data to the range [0, 1]. Then, using the SVM and random forest algorithms from the scikit-learn machine learning library, a dust particle data model is constructed using features such as particle concentration, trajectory, and velocity as input. The SVM algorithm used the RBF kernel function with a penalty coefficient C = 1.0 and a kernel parameter gamma = 0.1. The random forest algorithm used 100 decision trees, each with a maximum depth of 10. The model's performance was evaluated through 5-fold cross-validation, achieving an accuracy rate exceeding 95%. Using the established data model, the Prophet time series prediction algorithm and the multivariate linear regression algorithm were used to predict particle concentration trends over the next 24 hours, achieving a mean absolute percentage error (MAPE) of less than 10%. Meanwhile, the air pressure monitoring system collected air pressure data every minute with a resolution of 0.1 hPa. A Pearson correlation analysis of the air pressure data and particle concentration data revealed a correlation coefficient exceeding 0.8, indicating that changes in air pressure significantly affect particle concentration. Therefore, air pressure data was used as an additional feature, along with other features such as particle concentration, trajectory, and velocity, and fed into a multi-layer perceptron (MLP) neural network model to predict the air quality index (AQI) for the next 24 hours. The MLP model uses three hidden layers, each containing 64, 32, and 16 neurons, respectively. The activation function is ReLU, the optimization algorithm is Adam, and the learning rate is 0.01. Weather forecast data is used to estimate air pressure changes over the next 24 hours. This is input into the trained MLP model to obtain the corresponding AQI forecast. Finally, the TensorBoard visualization tool is used to monitor the model's training progress and performance in real time. Early stopping and learning rate decay strategies are used to prevent model overfitting. Through continuous iterative optimization, the mean absolute error (MAE) of the AQI forecast is kept within 5.

[0094] In other embodiments of the present disclosure, corresponding models can also be established based on the above ideas. For example, in coastal areas, due to the proximity to seawater, the salinity and humidity of the air will also affect the accuracy and safety of cable plugging. The above method can be used to establish a humidity model and / or salinity model to predict the air quality.

[0095] In step S102, noise and errors in the dust particle data are removed through a cloud server to obtain processed dust particle data, the processed dust particle data is combined with the ambient pressure data, a first data set is obtained through a Kalman filter algorithm, and the first data set is stored in a predefined format.

[0096] Specifically, high-frequency noise and random errors in the data are removed by wavelet threshold denoising method;

[0097] The signal processing module extracts features from the filtered dust particle data to obtain key feature parameters, including the concentration, particle size distribution, and movement speed of the dust particles;

[0098] Real-time air pressure data is acquired through an ambient air pressure monitoring system, and the air pressure data is time-synchronized and aligned with the processed dust particle data to obtain synchronized dust particle data and air pressure data;

[0099] fusing the synchronized dust particle data and air pressure data using a Kalman filter algorithm to obtain a first data set;

[0100] The first data set includes the concentration, particle size distribution and movement speed of dust particles and ambient air pressure data;

[0101] Organizing and packaging the first data set through a predefined data format and structure, and adding metadata and timestamp information;

[0102] The first data set is stored in a document-type NoSQL database such as MongoDB.

[0103] More specifically, the cloud server uses a signal processing module to remove noise and errors in the dust particle data, combines the processed dust particle data with the ambient pressure data, uses a Kalman filter algorithm to construct a first data set, and stores it in a predefined format.

[0104] The cloud server preprocesses the received dust particle data through the signal processing module, using wavelet threshold denoising to remove high-frequency noise and random errors from the data. The signal processing module then performs feature extraction on the filtered dust particle data, obtaining key characteristic parameters such as particle concentration, size distribution, and velocity. The cloud server obtains real-time air pressure data from the ambient air pressure monitoring system and time-aligns this air pressure data with the processed dust particle data. The Kalman filter algorithm fuses the synchronized dust particle and air pressure data. By establishing a state-space model and an observation model, the system state is recursively estimated to achieve the optimal data fusion result. The state vector includes the position and velocity of the dust particles, while the observation vector includes the concentration and size distribution data measured by the sensors. The Kalman filter algorithm initializes the state estimate and error covariance matrix, setting initial values ​​based on prior knowledge. During the prediction process, the state transition matrix and control input are used to predict the current state and calculate the prediction error covariance matrix. During the update process, the observations and the observation matrix are used to calculate the Kalman gain and update the state estimate and error covariance matrix. The formulas for the prediction and update process are as follows:

[0105] During the prediction process, the state prediction is x_pred = A*x_est + B*u;

[0106] The error covariance prediction is P_pred = A*P_est*A^T+Q;

[0107] During the update process, the Kalman gain K = P_pred*H^T*(H*P_pred*H^T+R)^(-1) is calculated;

[0108] The state estimate is updated to x_est = x_pred + K*(zH*x_pred);

[0109] Error covariance is updated to P_est = (IK*H)*P_pred;

[0110] Where A is the state transition matrix, B is the control input matrix, Q is the process noise covariance matrix, H is the observation matrix, R is the observation noise covariance matrix, and I is the identity matrix. The Kalman filter algorithm iterates the prediction and update process until convergence is reached or all data is processed, minimizing the variance of the estimation error. The fused data includes dust particle concentration, particle size distribution, velocity, and ambient air pressure data, forming the first dataset. The cloud server organizes and packages the first dataset according to a predefined data format and structure, adding metadata and timestamp information. The first dataset is stored in MongoDB, a document-based NoSQL database, leveraging its flexible data model and high scalability to store and manage heterogeneous first datasets. The database adopts a distributed architecture, using data sharding and replication mechanisms. The cloud server indexes the stored first dataset, accelerating data retrieval and analysis.

[0111] For example, the signal processing module preprocesses dust particle data using a wavelet threshold denoising method. The Daubechies4 wavelet basis function is used to perform a five-layer decomposition of the data. Noise in high-frequency detail coefficients is removed using a threshold parameter λ = σsqrt(2log(N)), where σ is the noise standard deviation and N is the data length. During feature extraction, particle image velocimetry is used to calculate particle velocity. Cross-correlation is performed on the image sequence to obtain the particle displacement vector. Combined with the image sampling interval, the velocity resolution reaches 0.1 m / s. When the Kalman filter algorithm fuses dust particle data with air pressure data, the state vector includes the particle position (x, y, z) and velocity (vx, vy, vz), and the observation vector includes the particle concentration, diameter, and air pressure. The initial state estimate is calculated based on the first image frame. The process noise covariance matrix Q is set based on the particle acceleration standard deviation, and the observation noise covariance matrix R is set based on the sensor's measurement error. The state transfer matrix A in the prediction step accounts for the uniform motion of the particles, while the observation matrix H in the update step relates the state variables to the observed quantities. The prediction and update steps were iterated 50 times, processing 100 data points each time, equivalent to 5 seconds of data. The fused first dataset was packaged in JSON format, with each data point containing a timestamp, particle concentration, diameter, velocity, and pressure fields. The MongoDB database uses the WiredTiger storage engine, distributing data across four shard nodes through hash sharding, with each shard node having two replicas to ensure data reliability. Indexing the timestamp field increased query speed by over 10 times.

[0112] In step S103, initial parameters of a particle swarm optimization model are set through a cloud server, and the first data set is input into the particle swarm optimization model to train the particle swarm optimization model; the initial parameters include the number of particles, speed, and position; and the particle swarm optimization model is used to generate a prediction result including the movement trend of dust.

[0113] Specifically, the number of particles is selected based on the dimension, complexity, and computing resource factors of the first data set; and the initial velocity and position of the particles are generated by a random function;

[0114] The particle swarm optimization model evaluates the optimization performance of each particle through a fitness function;

[0115] Setting a convergence condition, wherein the particle swarm optimization model iterates according to the convergence condition to obtain a prediction model for generating a prediction result including a motion trend of dust;

[0116] The convergence conditions include:

[0117] Set a maximum number of iterations. When the maximum number of iterations is reached, the particle swarm optimization model is considered to have converged.

[0118] Setting a minimum fitness threshold, when the optimal fitness value of multiple consecutive iterations changes less than the minimum fitness threshold, it is considered that the particle swarm optimization model has converged;

[0119] Setting a minimum particle position change threshold, when the particle position change of multiple consecutive iterations is less than the minimum particle position change threshold, the particle swarm optimization model is considered to have converged;

[0120] If the particle swarm optimization model satisfies one or more of the three convergence conditions, the particle swarm optimization model completes the iteration to obtain a prediction model for generating a prediction result including the movement trend of dust;

[0121] The prediction model is used to perform prediction analysis on the newly collected dust particle data to generate the dust movement trend in the future.

[0122] More specifically, the cloud server sets the initial parameters of the particle swarm optimization model, including the number, speed, and position of particles, and inputs the first data set into the particle swarm optimization model; training the particle swarm optimization model involves continuously adjusting the position of the particle swarm in the solution space to determine the optimal solution for the movement law and adsorption pattern of dust particles, so that the particle swarm optimization model generates a prediction result that includes the movement trend of dust.

[0123] The cloud server sets the initial parameters of the particle swarm optimization model based on the characteristic dimensions and data volume of the first dataset. Taking into account the dataset's dimensionality, complexity, and computing resources, the cloud server experimentally compares different particle numbers to select the particle number that achieves good optimization results within a reasonable timeframe. If the dataset is high-dimensional or complex, the particle number is increased; if computing resources are limited, the particle number is reduced. The initial velocity and position of the particles are generated using a random function. The cloud server inputs the first dataset into the particle swarm optimization model. The dataset includes information on dust particle concentration, size distribution, velocity, and ambient pressure; preferably, it also includes data on the amount of dust adsorbed on various surfaces. The particle swarm optimization model evaluates the optimization performance of each particle using a fitness function. The fitness function combines the accuracy of the dust motion trend prediction and the accuracy of the adsorption amount prediction. For dust motion trend prediction, the mean squared error (MSE) and mean absolute error (MAE) are used to measure the deviation between the predicted and actual values. For adsorption amount prediction, the relative error (RE) and coefficient of determination (R-square) are used to measure the fit between the predicted and actual values. The weighted average of the results of each evaluation metric is used to generate a comprehensive prediction accuracy score, which is used as part of the fitness function. During model training, the particle swarm continuously updates its velocity and position in the solution space. The particle's movement direction and step size are adjusted using the individual optimal and global optimal metrics to ensure continuous convergence toward the optimal solution. The individual optimal refers to the optimal solution found by a single particle in the previous search, while the global optimal refers to the optimal solution found by the entire particle swarm in the current search. The particle's velocity and position are updated by comparing its current fitness with the fitness of the corresponding individual optimal and global optimal values. The number of iterations is set based on the convergence speed and performance requirements of the particle swarm optimization algorithm. Experimental comparisons of different numbers of iterations are used to select the number of iterations that achieves good convergence within a reasonable timeframe. If multiple iterations fail to significantly improve the optimal solution, the iteration is terminated early. An upper limit is also set to prevent the algorithm from entering an infinite loop. Each iteration, the best particles are selected based on the fitness function to update their velocity and position, while the remaining particles are randomly generated. Through continuous iterative optimization, the particle swarm eventually converges to the optimal solution for the dust particle motion and adsorption patterns. The convergence criteria are based on the following three aspects: setting a maximum number of iterations, when the maximum number of iterations is reached, the algorithm is considered to have converged; setting a minimum fitness threshold, when the change in the optimal fitness value for multiple consecutive iterations is less than the minimum fitness threshold, the algorithm is considered to have converged; setting a minimum particle position change threshold, when the change in particle position for multiple consecutive iterations is less than the minimum particle position change threshold, the algorithm is considered to have converged. Combining these three convergence criteria can prevent the algorithm from stopping iterations too early or too late.Based on the trained prediction model, the cloud server performs predictive analysis on newly collected dust particle data, generating forecasts for dust movement trends and adsorption over a specific timeframe. The forecast timeframe can be customized. The prediction results are visualized using graphs and heat maps to illustrate the spatial and temporal distribution of dust concentration and adsorption.

[0124] For example, based on the feature dimensions (e.g., 20 features) and data volume (e.g., 10,000 samples) of the comprehensive dataset, the cloud server selects a particle number (e.g., 100) that achieves optimal optimization results within a reasonable timeframe (e.g., 10 minutes) by experimentally comparing different particle numbers (e.g., 50, 100, and 200). The initial particle velocity and position are generated using a random function, with the velocity range being [-1, 1] and the position range covering the entire solution space. The cloud server inputs the first dataset, which includes information on dust particle concentration, size distribution, velocity, and ambient pressure, as well as data on the amount of dust adsorbed on various surfaces, into the particle swarm optimization model. The particle swarm optimization model evaluates the optimization performance of each particle using a fitness function. For dust motion trend prediction, the mean squared error (MSE) and mean absolute error (MAE) are used as evaluation metrics, with weights of 0.6 and 0.4, respectively. For adsorption prediction, the relative error (RE) and coefficient of determination (R-square) are used as evaluation metrics, with weights of 0.7 and 0.3, respectively. The weighted average of the results of each evaluation metric is used to generate a comprehensive prediction accuracy score, which is used as part of the fitness function. During model training, the particle swarm continuously updates its velocity and position in the solution space. Using both individual and global optimality metrics, the particle's movement direction and step size are adjusted to ensure continuous convergence toward the optimal solution. By comparing different numbers of iterations (e.g., 500, 1000, and 2000), an iteration number (e.g., 1000) is selected to achieve good convergence within a reasonable timeframe (e.g., 30 minutes). If the fitness value of the optimal solution fails to improve by 1% after 50 consecutive iterations, the iteration is terminated early. An upper limit of 5000 iterations is also set to prevent the algorithm from entering an infinite loop. Each iteration, the top 20% of particles selected based on the fitness function are updated for velocity and position, while the remaining particles are randomly generated. The following three convergence criteria are considered: reaching the maximum number of iterations of 1000; the optimal fitness value changing by less than 0.01 for 30 consecutive iterations; and the particle position changing by less than 0.001 for 30 consecutive iterations. When any convergence condition is met, the algorithm is considered to have converged to the optimal solution. Based on the trained prediction model, the cloud server performs predictive analysis on newly collected dust particle data, generating dust movement trends and adsorption capacity forecasts for the next 24, 48, and 72 hours. The prediction results are presented as graphs and heat maps. The graphs show the changing trends of dust concentration and adsorption capacity at different time scales (e.g., hourly and every six hours), while the heat maps display the distribution of dust concentration and adsorption capacity at different spatial locations (e.g., different regions and different altitudes).

[0125] Step S104: obtain the output results of the particle swarm optimization model through the built-in system of the dust removal instrument, and analyze the movement trend and concentration change of the dust particles; obtain the insulation status of the cable joint through the insulation status sensor of the dust removal instrument; construct a second data set based on the movement trend of the dust particles, the concentration change and the insulation status of the cable joint; the second data set is used to adjust the operating frequency and cleaning intensity of the dust removal instrument.

[0126] Specifically, the output results of the particle swarm optimization model are obtained in real time through a wireless network; the position coordinates, movement speed and direction information of dust particles at different time points, and the numerical change curve of dust concentration are obtained;

[0127] Obtaining the motion data and concentration data of dust particles through analysis; correlating the motion data and concentration data of dust particles with the spatial position information of the dust removal instrument to determine the density and distribution of dust particles encountered by the dust removal instrument during future operation;

[0128] Obtaining an insulation resistance value threshold range and a dielectric loss factor threshold range, monitoring the insulation resistance value and dielectric loss factor at the cable joint in real time through the insulation status sensor of the dust removal instrument, and comparing the collected insulation resistance value with a preset insulation resistance value threshold range, and comparing the collected dielectric loss factor with a preset dielectric loss factor threshold range;

[0129] When the insulation resistance value exceeds the preset insulation resistance value threshold range, or when the dielectric loss factor exceeds the preset dielectric loss factor threshold range, it is determined that the insulation state is abnormal and a warning signal is triggered;

[0130] Correlating the abnormal insulation state data with the dust particle movement and concentration data at the corresponding time to construct a second data set;

[0131] Based on the AdaBoost algorithm, a correlation model between dust pollution and insulation abnormality was established. The probability distribution of insulation abnormality of cable joints under different dust particle concentrations and movement trends was obtained through the correlation model.

[0132] Adjust the operating frequency and cleaning intensity of dust removal equipment based on the predicted dust particle concentration and the probability of abnormal insulation status;

[0133] According to the model's predicted probability of insulation abnormality, the operating frequency and cleaning intensity of the dust removal equipment are divided into low, medium, and high levels. A probability threshold is preset for each level, namely the low probability threshold, the medium probability threshold, and the high probability threshold.

[0134] When the predicted dust particle concentration or insulation state abnormal probability exceeds the low-level probability threshold, the operating frequency and cleaning intensity of the dust removal equipment are increased;

[0135] When the predicted dust particle concentration and insulation state abnormal probability are lower than the low-level probability threshold, the operating frequency and cleaning intensity of the dust removal equipment are reduced;

[0136] According to the analysis results of the correlation model, the high-risk time window of abnormal insulation status of the cable joint is predicted. Before the high-risk time window, the cable joint is dusted and cleaned according to the operating frequency and cleaning intensity of the dust removal instrument corresponding to the probability threshold level of the high-risk time window.

[0137] More specifically, the dust removal instrument's built-in system obtains the output results of the particle swarm optimization model and analyzes the movement trend and concentration changes of the dust; the dust removal instrument's insulation status sensor monitors the insulation status of the cable joint in real time; and a second data set is constructed by combining the movement trend and concentration changes of dust particles and the insulation status of the cable joint.

[0138] The dust removal instrument's built-in system uses a wireless network to obtain real-time output from a particle swarm optimization model hosted on a cloud server. This output includes predicted dust particle movement trends and concentration changes over time. The built-in system analyzes and extracts this predicted data, determining the position coordinates, velocity, and direction of dust particles at different points in time, as well as a numerical curve of dust concentration. The built-in system correlates this analyzed dust movement and concentration data with the dust removal instrument's own spatial location information to determine the density and distribution of dust particles expected to be encountered during future operation, providing a basis for formulating subsequent cleaning strategies. The dust removal instrument's insulation status sensor uses a capacitive or resistive measurement principle to monitor the insulation resistance and dielectric loss factor at cable connectors in real time. The sensor collects data at regular intervals and compares the collected insulation resistance and dielectric loss factor values ​​with pre-set thresholds. The threshold settings require optimization and adjustment based on actual engineering experience and equipment characteristics. By collecting extensive historical operating data and analyzing the distribution of insulation resistance and dielectric loss factor, combined with expert experience and equipment characteristics, multiple threshold levels are established, with different warning and action measures implemented based on the threshold levels. When the insulation resistance value or dielectric loss factor exceeds the threshold, the insulation state is determined to be abnormal, triggering an early warning signal. The built-in system correlates the abnormal insulation state data with the dust particle movement and concentration data at the corresponding moment. Using the timestamp as the correlation field, the two data types are aligned in time to form a correlated dataset containing dust particle concentration, movement trend, and insulation state fields, thus constructing a second dataset. The built-in system analyzes and mines the second dataset, identifying dust contamination and insulation state abnormalities through manual annotation or setting certain threshold conditions. The annotation results are then correlated with other fields in the second dataset to form a complete training dataset. Using the AdaBoost algorithm, a correlation model is established between dust contamination and insulation state abnormalities, deriving the probability distribution of cable joint insulation state abnormalities under different dust particle concentrations and movement trends. Based on the analysis results of the correlation model, the built-in system dynamically adjusts the operating parameters and cleaning strategy of the dust removal equipment. A fuzzy control algorithm is designed to dynamically adjust the dust removal equipment's operating frequency, cleaning intensity, and dust removal cycle parameters based on the predicted dust particle concentration and insulation state abnormality probability. The control algorithm must balance dust removal effectiveness and energy consumption to achieve optimal overall performance. An adaptive learning mechanism is introduced to adjust and optimize the control algorithm parameters online based on actual operational feedback and performance evaluation. Based on the model's predicted probability of insulation abnormality, the dust removal equipment's operating frequency and cleaning intensity are categorized into three levels: low, medium, and high, with a preset probability threshold for each level.When the predicted dust particle concentration or the probability of an abnormal insulation state exceeds a low-level probability threshold, the control algorithm increases the frequency and intensity of dust removal equipment, increasing the frequency and duration of dust removal at the cable joints. When the predicted dust particle concentration and the probability of an abnormal insulation state fall below the low-level probability threshold, the control algorithm decreases the frequency and intensity of dust removal equipment, extending the dust removal cycle at the cable joints and saving energy and resources. Based on the analysis results of the correlation model, the built-in system predicts high-risk windows for abnormal insulation state at cable joints within a certain period of time. Preventive dust removal and cleaning of the cable joints are performed in advance of these high-risk windows to reduce the risk of abnormal insulation state.

[0139] For example, the dust removal instrument's built-in system acquires the output of the particle swarm optimization model in real time via an IEEE 802.11ac wireless network at a rate of 150 Mbps. This includes predicted data on dust particle movement trends and concentration changes over the next 24 hours. The built-in system parses the predicted data in JSON format, extracting information such as the dust particle's location coordinates (with an accuracy of 0.1 meter), velocity (with an accuracy of 0.1 meter / second), and direction (with an accuracy of 1 degree), as well as a numerical curve of dust concentration (with a time granularity of 1 hour). The built-in system then performs spatial correlation analysis with the dust removal instrument's GPS location information (with an accuracy of 1 meter) to identify high-pollution areas (dust concentrations exceeding 1000 particles / cubic centimeter) along the instrument's future operating path. The insulation status sensor uses a capacitive measurement principle with a range of 0.1pF to 10pF and an accuracy of 0.01pF, collecting data every 1 second. The sensor is factory-calibrated to the safe threshold ranges for insulation resistance and dielectric loss factor (insulation resistance greater than 100 MΩ, dielectric loss factor less than 0.01). The built-in system aligns the timestamps of abnormal insulation status data (data exceeding the threshold range) with the corresponding dust particle data, constructing a linked dataset containing fields such as timestamp, dust particle concentration, movement speed, movement direction, insulation resistance, and dielectric loss factor. The built-in system cleans the linked dataset to remove missing and outliers, then scales the data using Z-score normalization. Using the AdaBoost algorithm, a binary classification association model is constructed between dust contamination and insulation status anomalies, using dust particle concentration, movement speed, and movement direction as features and whether the insulation status is abnormal or not as a label. The model uses 10-fold cross-validation, achieving an average accuracy of over 95%. Based on the association model, the built-in system designed a fuzzy control algorithm. Based on the model's predicted probability of insulation abnormality, the dust collector's operating frequency and cleaning intensity are categorized as low, medium, and high, with corresponding probability thresholds of 0.2, 0.5, and 0.8, respectively. When the predicted probability is less than 0.2, the dust collector operates once daily at a cleaning intensity of 1; when the predicted probability is between 0.2 and 0.5, the dust collector operates twice daily at a cleaning intensity of 2; and when the predicted probability is greater than 0.5, the dust collector operates three times daily at a cleaning intensity of 3. The dust collector's operating hours are determined by the high-contamination time window predicted by the particle swarm optimization model. Operation begins one hour before the high-contamination time window and ceases one hour after the high-contamination time window. Through this fuzzy control algorithm, the dust collector can dynamically adjust its operating strategy based on the predicted dust contamination level and the risk of insulation abnormality, ensuring dust removal effectiveness while maximizing energy and cost savings.

[0140] Step S105, obtaining the working intensity of the dust removal instrument through the fuzzy logic controller in the dust removal instrument; the input parameters of the fuzzy logic controller include dust movement trend, concentration change and insulation status of the cable connector, and the output parameters are the working intensity of the dust removal instrument; the working intensity of the dust removal instrument includes voltage, current, working frequency, vibration frequency and wind speed.

[0141] Specifically, the movement trend and concentration changes of dust particles and the insulation status of cable joints are obtained;

[0142] The dust concentration is divided into: low dust concentration, medium dust concentration and high dust concentration;

[0143] The dust movement trend is divided into: steady dust movement trend, slowly rising dust movement trend and rapidly rising dust movement trend;

[0144] The cable joint insulation status is divided into: normal cable joint insulation status, slightly abnormal cable joint insulation status and seriously abnormal cable joint insulation status;

[0145] According to Mamdan i reasoning method, a fuzzy rule base is constructed;

[0146] Through the center of gravity defuzzification method, the result of fuzzy reasoning is converted into the specific working parameters of the dust removal instrument; and an instruction is issued to make the dust removal instrument work according to the specific working parameters.

[0147] More specifically, the dust removal instrument includes a fuzzy logic controller, the input parameters of which include dust movement trends, concentration changes, and the insulation status of cable connectors, and the output parameters include the working intensity of the dust removal instrument, including voltage, current, operating frequency, vibration frequency, and wind speed.

[0148] The fuzzy logic controller in the dust removal instrument uses the RS-485 bus to acquire real-time input parameters, including dust particle movement trends, concentration changes, and cable joint insulation status. Data on dust particle movement trends and concentration changes come from the dust removal instrument's built-in dust sensor and are collected periodically via the RS-485 bus. Cable joint insulation status data comes from an insulation status monitoring device and is collected periodically via the RS-485 bus. The controller uses a triangular membership function to fuzzify the input parameters, classifying dust concentration into three fuzzy subsets: low, medium, and high. Dust movement trends are classified into stable, slowly increasing, and rapidly increasing. Cable joint insulation status is classified into normal, slightly abnormal, and severely abnormal. The fuzzy logic controller uses the Mamdan inference method to construct a fuzzy rule base. The premise of each rule is composed of fuzzy subsets of the input parameters, and the conclusion is composed of fuzzy subsets of the output parameters. If the dust concentration is high, the dust movement trend is rapidly rising, and the insulation state of the cable joint is seriously abnormal, then the working intensity of the dust removal instrument is high. The fuzzy logic controller uses the center of gravity defuzzification method to convert the results of fuzzy reasoning into specific working parameters of the dust removal instrument. Assume that the membership function of the working intensity of the dust removal instrument obtained by fuzzy reasoning is μ(x), where x is the value of the working intensity. Discretize μ(x) into n points, the horizontal coordinate of each point is xi, the vertical coordinate is μ(xi), i=1, 2, ..., n. Calculate the horizontal coordinate of the center of gravity as:

[0149] x*=(x1μ(x1)+x2μ(x2)+…+xnμ(xn)) / (μ(x1)+μ(x2)+…+μ(xn)).

[0150] x represents the specific value of the dust removal instrument's operating intensity after defuzzification. The controller divides the dust removal instrument's operating voltage into three fuzzy subsets: low, medium, and high. The operating current is divided into three fuzzy subsets: low, medium, and high. The operating frequency is divided into three fuzzy subsets: low, medium, and high. The vibration frequency is divided into three fuzzy subsets: low, medium, and high. The operating wind speed is divided into three fuzzy subsets: low, medium, and high. Based on the position of x* in each fuzzy subset, the corresponding specific values ​​for operating voltage, current, frequency, vibration frequency, and wind speed are determined and transmitted to the dust removal instrument's actuator via the RS-485 bus. Based on the received operating parameters, the dust removal instrument's actuator adjusts the power module's output voltage and current, controls the vibration frequency of the vibration motor, and changes the speed and air volume of the dust collection fan, achieving precise control of dust removal intensity. The fuzzy logic controller also has adaptive learning capabilities. By online monitoring of the dust removal instrument's actual operating performance, it uses a neural network algorithm to dynamically optimize and adjust the fuzzy rule base. A feedforward neural network is used. Input parameters include dust concentration, dust movement trend, and cable joint insulation status; output parameters include the dust removal instrument's operating voltage, current, frequency, vibration frequency, and wind speed. The activation functions for the hidden and output layers are sigmoid functions. The neural network is trained using a backpropagation algorithm. At regular intervals, new data is collected from the dust removal instrument's dust sensors and insulation status monitoring devices. These data serve as training samples for incremental training of the neural network, enabling dynamic optimization of the fuzzy rule base. The optimization objectives are to minimize the dust removal instrument's energy consumption and dust concentration and maximize the cable joint's insulation resistance. By setting appropriate weight coefficients, the multi-objective optimization problem is transformed into a single-objective one.

[0151] For example, a fuzzy logic controller acquires dust particle movement trend and concentration change data from the dust removal instrument's built-in dust sensor every 1 second via an RS-485 bus at a baud rate of 9600bps. It also acquires cable joint insulation status data from the insulation status monitoring device every 5 seconds. The controller uses a triangular membership function to fuzzify the input parameters, dividing the domain of dust concentration into 0-2000 particles / cubic centimeter, the domain of dust movement trend into 0-30 particles / cubic centimeter / hour, and the domain of cable joint insulation status into 0-2000MΩ. The Mamdan inference method uses minimum and maximum membership synthesis rules to match fuzzy subsets of the input parameters using 27 I F-THEN rules to calculate the membership of the output parameters. For example, the matching degree for the rule "IF dust concentration is high AND dust movement trend is rapidly rising AND cable joint insulation condition is severely abnormal THEN dust removal equipment operating intensity is high" is min(μhigh(xconcentration),μrapidly rising(xtrend),μseverely abnormal(xinsulation)) = 0.8. The centroid defuzzification method discretizes the membership distribution curve μ(x) of the output parameter within its domain into 100 points, using the following formula:

[0152] x*=(x1μ(x1)+x2μ(x2)+……+x100μ(x100)) / (μ(x1)+μ(x2)+……+μ(x100))

[0153] According to the above formula, the horizontal coordinate x of the center of gravity is calculated as the specific work intensity value after defuzzification. If x* = 0.75, the fuzzy subset partitioning table of the working parameters is queried, and the operating voltage is 250V, the operating current is 2.25A, the operating frequency is 26.25Hz, the vibration frequency is 32.5Hz, and the operating wind speed is 17.25m / s. These values ​​are then transmitted to the actuator of the dust removal instrument via the RS-485 bus at a baud rate of 19200bps. A three-layer feedforward neural network is incrementally trained using 100 sets of new data collected by the dust removal instrument every hour. The mean square error is used as the loss function, and the weight matrix is ​​updated using batch gradient descent. The learning rate is 0.01, the momentum factor is 0.9, and the maximum number of iterations is 1000. The energy consumption weight coefficient is set to 0.5, the dust concentration weight coefficient is set to 0.3, and the insulation resistance weight coefficient is set to 0.2. The original objective function f(x) = 0.5 energy consumption + 0.3 dust concentration - 0.2 * insulation resistance value is transformed into minimizing f(x). The genetic algorithm is used to search for the optimal weight coefficient combination. The population size is 50, the crossover probability is 0.8, the mutation probability is 0.1, and the evolution is carried out for 100 generations. The optimal weight coefficient combination [0.6, 0.2, 0.2] is obtained as the training target of the neural network model, so that the fuzzy rule base can be dynamically optimized according to changes in environmental conditions and equipment status.

[0154] Step S106, judging whether the insulation performance of the cable joint meets the safety standard based on the insulation status of the cable joint, if the insulation performance of the cable joint meets the safety standard, issuing an instruction to perform the plugging operation of the cable joint; if the insulation performance of the cable joint does not meet the safety standard, inputting the second data set into the fuzzy logic controller, obtaining output parameters and issuing an instruction to make the dust removal device perform the dust removal operation according to the output parameters of the fuzzy logic controller; by analyzing the insulation status of the cable joint during dust removal, continuously issuing instructions to make the dust removal device perform the dust removal operation according to the output parameters of the fuzzy logic controller until the insulation performance of the cable joint meets the safety standard.

[0155] Specifically, the insulation status index threshold is preset, the insulation resistance value and dielectric loss factor of the cable joint are collected, and the insulation status index IS is calculated:

[0156] IS=0.7×(R / R0)+0.3×(tanδ0 / tanδ),

[0157] Where R is the measured insulation resistance value, R0 is the insulation resistance threshold, tanδ is the measured dielectric loss factor, and tanδ0 is the dielectric loss factor threshold;

[0158] When IS is greater than or equal to the insulation state index threshold, it is determined that the insulation performance of the cable joint meets the safety standard; when IS is less than the insulation state index threshold, it is determined that the insulation performance of the cable joint does not meet the safety standard;

[0159] If the insulation performance of the cable connector meets the safety standard, an instruction to perform the plugging operation of the cable connector is issued;

[0160] If the insulation performance of the cable joint does not meet the safety standard, the second data set is input into the fuzzy logic controller;

[0161] According to Mamdan i reasoning method, a fuzzy rule base is constructed;

[0162] By using the center of gravity defuzzification method, the result of fuzzy reasoning is converted into the specific working parameters of the dust removal instrument; and an instruction is issued to make the dust removal instrument work according to the specific working parameters;

[0163] When the insulation state index IS is greater than the insulation state index threshold for multiple consecutive times, it is determined that the insulation performance of the cable joint has reached the safety standard, and an instruction to perform the plugging operation of the cable joint is issued;

[0164] Collect the insertion depth of the connector, the displacement and speed of the plugging mechanism, calculate the deviation between the actual insertion depth of the connector and the target depth, and adjust the movement of the plugging mechanism according to the deviation between the actual insertion depth and the target depth until the plugging operation of the cable connector is completed;

[0165] After completing the plugging operation of the cable connector, collect the axial compression force and judge whether the required tightening degree is achieved based on the axial compression force.

[0166] More specifically, based on the insulation status of the cable joint, it is determined whether the insulation performance of the cable joint meets the safety standard; if the insulation performance does not meet the standard, the second data set is input into the fuzzy logic controller to allow the dust removal instrument to perform dust removal operations according to the output parameters of the fuzzy logic controller; the insulation status of the cable joint during dust removal is analyzed, and the dust removal operation is continued until the safety standard is met; if the insulation status meets the safety standard, an instruction is issued to perform the cable joint plugging operation.

[0167] The insulation condition monitoring device collects the insulation resistance and dielectric loss factor of the cable joint in real time and transmits the collected data to the insulation performance evaluation module via Industrial Ethernet. The insulation performance evaluation module sets the insulation resistance threshold and the dielectric loss factor (tanδ) threshold based on the voltage level of the cable joint. The evaluation module divides the collected insulation resistance and dielectric loss factor by their respective thresholds to obtain relative values. The evaluation module then calculates the insulation condition index (IS) as 0.7 × (R / R0) + 0.3 × (tanδ0 / tanδ), where R is the measured insulation resistance, R0 is the insulation resistance threshold, tanδ is the measured dielectric loss factor, and tanδ0 is the dielectric loss factor threshold. When IS is greater than or equal to the insulation condition index threshold, the insulation performance is considered to meet the standard. When IS is less than the insulation condition index threshold, the insulation performance is considered to meet the standard. If the insulation performance evaluation result fails to meet the standard, the insulation performance evaluation module immediately sends a warning signal to the data fusion module. The data fusion module then transmits the insulation condition monitoring data, dust concentration, and movement trend data from the second dataset to the fuzzy logic controller via the ModbusTCP protocol. The fuzzy logic controller uses a Mamdan I-type fuzzy inference system and sets several IF-THEN-style fuzzy rules. If the insulation state index (IS) is low and the dust concentration is high, the dust removal intensity should be increased. The antecedent of the fuzzy rule is composed of fuzzy subsets of the input variables, and the consequent is composed of fuzzy subsets of the output variables. The minimum membership method is used for rule matching and activation. During the fuzzy inference process, the inference results of each rule are aggregated to obtain a fuzzy subset of the output variables. This is then defuzzified using the centroid method to obtain a clear value for the dust removal intensity. The optimal operating parameter combination for the dust removal instrument, including operating voltage, current, frequency, vibration frequency, and wind speed, is then calculated. Control commands are then sent to the dust removal instrument's actuator via the Modbus TCP protocol. Based on the received control commands, the dust removal instrument's actuator initiates the dust removal operation, adjusts the output voltage and current of the power module, controls the vibration frequency of the vibration motor, and changes the speed and air volume of the dust suction fan, achieving centralized dust removal of the cable connector and its surroundings. During the dust removal process, the insulation status monitoring device continuously collects the insulation parameters of the cable joint. The insulation performance evaluation module calculates the insulation status index (IS) in real time. When the evaluation results exceed the insulation status index threshold for multiple consecutive times, the dust removal operation is determined to be effective and a dust removal completion signal is sent to the data fusion module. After receiving the dust removal completion signal, the data fusion module sends a stop command to the dust removal instrument and writes the control bit in the dust removal instrument's Modbus holding register. After receiving the stop command, the dust removal instrument compares the control bit value with the preset stop flag bit. If they match, the dust removal operation is immediately stopped and a stop confirmation signal is returned to the data fusion module. At the same time, the cable joint insulation status monitoring data and dust removal operation parameter information are recorded in the database, forming a cable joint dust removal operation report, providing data support for subsequent preventive testing and condition-based maintenance.After the dust removal instrument stops operating, the data fusion module sends a connector-ready signal to the cable connector operation control module. Upon receiving this signal, the cable connector operation control module executes the cable connector insertion operation. An inductive displacement sensor is installed on the cable connector housing to measure the connector's insertion depth in real time. A photoelectric encoder is installed on the plugging mechanism to measure its displacement and speed in real time. Feedback from the displacement sensor and encoder is used to calculate the deviation between the connector's actual insertion depth and the target depth. A PID control algorithm is then used to adjust the plugging mechanism's movement, ensuring precise alignment and insertion of the male and female connectors. After insertion, a pressure sensor measures the axial compression force of the cable connector to determine whether the required tightness has been achieved. A contact-type continuity tester is used to test the cable path for continuity to ensure reliable insertion. After the insertion operation is complete, the cable connector operation control module reads the latest data from the insulation status monitoring device to re-verify the insulation performance of the cable connector. If multiple consecutive test results meet the requirements, insulation maintenance and plugging of the entire cable connector are complete, and the system returns to normal monitoring. Throughout the entire process, the fuzzy logic controller uses an adaptive adjustment mechanism to dynamically optimize fuzzy rules and membership functions based on historical data and expert experience, and uses an objective function that integrates dust removal effect and energy consumption to continuously improve dust removal performance.

[0168] For example, the insulation condition monitoring device collects the insulation resistance and dielectric loss factor of the cable joint every minute, with a resolution of 0.1 MΩ and 1 × 10⁻⁶, respectively. These values ​​are transmitted to the insulation performance evaluation module via the RS-485 bus at a baud rate of 9600 bps. The evaluation module uses a segmented threshold judgment method. For cable joints with voltage levels of 10 kV and below, the insulation resistance threshold R0 is set to 100 MΩ, and the dielectric loss factor threshold tanδ0 is set to 40 × 10⁻⁴. After calculating the relative values, the insulation condition index is calculated using the weighted average formula IS = 0.7 × (R / R0) + 0.3 × (tanδ0 / tanδ). The weight coefficients are optimized using a decision tree algorithm. If IS is less than 0.9 three times consecutively, a warning interrupt is triggered in the data fusion module via the Modbus TCP protocol, and the collected 512 bytes of data are encapsulated in a Modbus data frame and sent to the fuzzy logic controller. Based on 125 preset fuzzy rules, the fuzzy logic controller uses the maximum-minimum composite inference method and a central average defuzzification method to determine the dust removal intensity clarity value. A table lookup method is then used to determine the five operating parameters of the dust removal instrument: the operating voltage range is 100V-300V with a 10V step size, and the frequency range is 10Hz-30Hz with a 1Hz step size. Upon receiving the Modbus control command, the dust removal instrument writes the dust removal intensity value to the Modbus coil, initiating the dust removal operation. Every 30 seconds, the Modbus coil transmits the current operating status (e.g., normal, fault, alarm, etc.) to the data fusion module. During the dust removal operation, the insulation performance evaluation module calculates the insulation resistance (IS) every two minutes. If the IS value is greater than or equal to 0.9 for three consecutive times, the Modbus predefined exception response code 0x0A is sent to the data fusion module, triggering a dust removal completion event. After receiving the 0x0A response code, the data fusion module writes the stop flag 0x55AA to the dust removal instrument's Modbus holding register. Upon detecting this flag, the dust removal instrument immediately shuts down and writes back 0xAA55 as confirmation. It also stores the most recent device operating data (such as accumulated operating time and number of faults) in the database's device log table. The inductive displacement sensor on the cable connector housing has a range of 0 mm to 100 mm and an accuracy of 0.1 mm. It transmits data every 5 milliseconds via a 4 mA to 20 mA current loop. The photoelectric encoder on the plug-in mechanism has a resolution of 1000 pulses per revolution and transmits displacement and velocity data every 1 millisecond via an RS-422 serial interface. The plug-in process is controlled using a three-loop closed-loop PID algorithm: position loop P = 2.5, I = 0.05, D = 0.01; velocity loop P = 10, I = 0.1, D = 0.05; and current loop P = 20, I = 1, D = 0.1.After the connection is complete, a pressure sensor measures the axial clamping force at a sampling frequency of 0.5Hz, with a range of 0N-1000N and an accuracy of 1N. A connection is considered complete when the clamping force stabilizes within the range of 800N±10N. A continuity tester outputs a 5V, 50mA DC signal, and successful connection is determined when the on-resistance is less than 1Ω. Finally, the cable connector operation control module reads data from the insulation status monitoring device and performs a t-test with a 95% confidence level. If the t-values ​​are within the critical value for three consecutive times and the on-resistance is less than 1Ω for three consecutive times, a "pass" flag is written to the connector status database, completing the connection. The fuzzy logic controller performs a daily self-learning optimization based on the dust removal performance and energy consumption data from the previous week. This optimization is performed using a genetic algorithm with a crossover probability of 0.8 and a mutation probability of 0.1. The optimal individual fuzzy rule base is updated to the controller's EPROM after 100 iterations. The objective function FIT = 0.8×(IS1-IS0)+0.2×(P0-P1), where IS0 and IS1 represent the insulation state index before and after dust removal, respectively, and P0 and P1 represent the energy consumption per unit time before and after dust removal, respectively. The fuzzy rule base is optimized by maximizing the objective function.

[0169] Step S107, by continuously monitoring the communication status between the cloud server, cable connector and dust removal instrument, ensure the stability of data transmission and collect real-time plugging data during the plugging process; analyze the real-time plugging data through the cloud server application data acquisition module to evaluate the accuracy and safety of the plugging operation; the real-time plugging data includes torque, insertion force and dust concentration.

[0170] Specifically, the communication status between the cloud server, cable connector, and dust removal instrument is monitored through the heartbeat mechanism, and the round-trip delay is recorded;

[0171] The token bucket algorithm is used to shape and limit the data transmission traffic between the cloud server, cable connector and dust removal equipment; the token generation rate is dynamically adjusted according to the water level of tokens passing through;

[0172] When the water level of the token bucket exceeds a certain percentage for a period of time, a traffic anomaly alarm is triggered;

[0173] Collect the torque, insertion force and dust concentration in the plugging environment during the plugging process as real-time plugging data;

[0174] Pre-process the real-time plug-in data and compress the data through the run-length encoding algorithm;

[0175] The real-time plug-in data is filtered and smoothed by the Kalman filter algorithm to obtain the plug-in data;

[0176] Establishing a plugging operation evaluation model for judging the accuracy and safety of the current plugging operation through a decision tree algorithm, inputting the plugging data into the plugging operation evaluation model; judging the accuracy and safety of the current plugging operation;

[0177] The plugging data is collected and clustered. The elbow method is used to evaluate different clustering numbers K to obtain the optimal clustering number. The plugging data is classified using the K-means algorithm. The number, proportion and parameter distribution status of various plugging operations are counted to generate a plugging operation quality report.

[0178] More specifically, during the plugging operation, the communication status between the cloud server, cable connector and dust removal instrument is continuously monitored to ensure the stability of data transmission and collect real-time plugging data during the plugging process, including torque, insertion force and dust concentration; the cloud server applies the data acquisition module to analyze the real-time plugging data and evaluate the accuracy and safety of the plugging operation.

[0179] The communication status monitoring module uses a heartbeat mechanism, sending heartbeat packets to the cloud server, cable connector, and dust removal equipment at regular intervals and recording the round-trip delay. If the round-trip delay of multiple consecutive heartbeat packets exceeds a certain time, or if multiple consecutive heartbeat packets go unanswered, a communication anomaly alarm is triggered and the timestamp, node ID, and anomaly type are recorded in the communication log database. The communication status monitoring module also monitors data transmission traffic between the cloud server, cable connector, and dust removal equipment, using a token bucket algorithm to shape and limit traffic. The token generation rate is adjusted based on the statistical distribution of historical data transmission traffic and traffic volatility. The token bucket capacity is set based on network latency and jitter characteristics to ensure that the impact of traffic bursts on the network can be effectively mitigated. If the token bucket water level exceeds a certain percentage for a period of time, a traffic anomaly alarm is triggered, and the token generation rate is dynamically adjusted based on the water level to achieve adaptive traffic control. The cable connector is equipped with a torque sensor, a pressure sensor, and a dust concentration sensor. The torque and pressure sensors collect torque and insertion force data during the plugging process at a set frequency, while the dust concentration sensor collects dust concentration data in the plugging environment at a set frequency. The sensors communicate with the data acquisition module using the industrial Ethernet protocol EtherCAT. The data acquisition module preprocesses the real-time plugging data, including timestamp alignment, data format conversion, and outlier filtering. It also compresses the data using a run-length encoding algorithm. The processed real-time plugging data is packaged into a JSON format and transmitted to the cloud server via the MQTT protocol with reliable transmission at QoS level 1. After receiving the real-time plugging data, the cloud server's data analysis engine uses the Kalman filter algorithm to filter and smooth the data to obtain the plugging data, which is then input into the plugging operation evaluation model. This model uses a decision tree algorithm based on the statistical distribution of historical plugging operation data to extract 11 feature indicators: peak value, slope, fluctuation range, RMS value, and crest factor of the torque signal; rise time, peak time, and steady-state value of the insertion force signal; and mean value, variance, and exceedance rate of the dust concentration signal. A ReliefF algorithm is then used to automatically select a subset of key features that have the greatest impact on plugging quality from the candidate feature set. A decision tree is generated using the CHAID algorithm. A grid search and 10-fold cross-validation method are used to select the optimal parameter combination for the decision tree, including the maximum depth of split nodes, minimum number of samples, and impurity measure. Plugging data flows through the decision tree classifier to determine the accuracy and safety of the current plugging operation. If the instantaneous torque or insertion force value exceeds the safety threshold multiple times in a row, the plugging operation is identified as a safety hazard, triggering an immediate safety alarm and notifying the cable connector operation control module to suspend plugging. The torque standard deviation, insertion force slope, and dust concentration are used to determine whether the plugging operation was correct.If the plugging operation is accurate, the current plugging parameters and environmental parameters are recorded in the plugging operation log database as an excellent plugging case. The data analysis engine performs cluster analysis on the recent plugging data at regular intervals, uses the elbow method to evaluate different clustering numbers K, selects the K value corresponding to the inflection point where the SSE decline rate slows down as the optimal clustering number, and uses the K-means algorithm to cluster the plugging data into three categories: excellent plugging, qualified plugging, and unqualified plugging. The number, proportion, and parameter distribution of each type of plugging operation are then counted to generate a plugging operation quality report, which is pushed to on-site operators and managers via a web service. The data analysis engine uses an incremental learning algorithm. Whenever the cumulative new plugging operation data reaches a certain threshold, a certain amount of data is randomly sampled as a training set, and the remaining data is used as a test set. The decision tree classifier and K-means clusterer are retrained and evaluated. Grid search and cross-validation are used to continuously optimize the parameters of the decision tree and clusterer, continuously improving the accuracy and reliability of the plugging operation quality assessment.

[0180] For example, the communication status monitoring module uses a UDP-based heartbeat mechanism. Heartbeat packets are 64 bytes long and contain information such as the node ID, timestamp, and sequence number. They are sent via the MQTT protocol with a QoS level of 0. Round-trip latency is calculated using the Ping-Pong algorithm. If three consecutive timeouts (RTT > 500ms) or two packet losses occur, the node status is marked as abnormal. Information such as the event timestamp, duration, and abnormality type is recorded and written to an abnormality log table in the MySQL database. Data transmission traffic is collected in real time via a network traffic probe once per second. Traffic shaping is performed using a token bucket algorithm, with a token generation rate set to 100 Mbps and a bucket depth of 8 MB. When the token bucket level exceeds 80% for five consecutive seconds, a traffic anomaly alarm is triggered. Information such as the alarm time, traffic value, and token bucket parameters is written to the traffic anomaly log table. Webhooks are used to notify the cloud management system to dynamically adjust the token generation rate in 10 Mbps increments. The cable connector features an integrated, spoke-type six-axis force sensor that simultaneously measures forces and torques in three orthogonal directions. The ranges are Fx / Fy ±1000N, Fz ±2000N, and Mx / My / Mz ±50Nm, with resolutions of 0.1N and 0.01Nm, respectively. Data is uploaded every 1ms via an EtherCAT bus with a 100MHz bandwidth. The dust concentration sensor, which uses a laser scattering principle, has a range of 0-10,000 particles per cubic centimeter, a resolution of 1 particle per cubic centimeter, and a sampling frequency of 10Hz. After preprocessing with linear interpolation, outlier removal, and digital filtering, the sensor data is compressed using Huffman coding, achieving a compression ratio of 3:1. The data is then packaged in JSON format and sent to a cloud data receiving module via the MQTT protocol (QoS level 1), with a transmission latency of less than 100ms. The plugging operation evaluation model constructs a decision tree based on the C4.5 algorithm. The optimal features are selected using information gain ratios and dynamically pruned using a heuristic method. The feature vector includes eight indicators, including peak value, slope, and fluctuation range of the force signal, and three indicators, including mean, standard deviation, and exceedance rate of the dust concentration signal. The training set consists of 10,000 historical plugging cases. A 10-fold cross-validation algorithm with a minimum leaf node sample size of 20 was used, achieving an accuracy rate exceeding 95%. When the torque exceeds 45 Nm or the insertion force exceeds 850 N, the decision tree issues a safety alert, triggering a plugging operation pause via the OPCUA protocol. When the feature vector falls within the normal plugging range, the plugging parameters are written to a table of excellent plugging cases in a SQLite database. The K-means clustering algorithm uses the maximum expectation algorithm for parameter estimation, and the elbow method determines the optimal number of clusters, K=3. Parallel computing is implemented using MapReduce, processing 10 minutes of data per minute. Clustering reports are generated and pushed to the Grafana dashboard.Incremental learning is triggered every time 1,000 new data are added. The Mini-Batch K-Means algorithm updates the cluster center and the AdaBoost algorithm updates the decision tree parameters. The training time is less than 10 seconds.

[0181] In the description of the present disclosure, it should be understood that the directions or positional relationships indicated by directional words such as "front, back, up, down, left, right", "horizontal, vertical, horizontal" and "top, bottom" are usually based on the directions or positional relationships shown in the accompanying drawings. They are only for the convenience of describing the present disclosure and simplifying the description. Unless otherwise specified, these directional words do not indicate or imply that the device or element referred to must have a specific direction or be constructed and operated in a specific direction. Therefore, they cannot be understood as limiting the scope of protection of the present disclosure.

[0182] Those skilled in the art can make various other corresponding changes and deformations based on the technical solutions and concepts described above, and all of these changes and deformations should fall within the scope of protection of the claims of this disclosure.

Claims

1. An intelligent inductive cable quick connector plugging method, characterized in that: The following steps are involved: The system uses environmental sensors to detect dust particle data in the air in real time, record the size and concentration of dust particles, and transmit the collected dust particle data to a cloud server via a wireless network. The environmental sensors include optical particle counters, laser radars, and cameras. The cameras are used to capture the movement path and speed of dust particles. The air pressure monitoring system detects ambient air pressure data in real time and transmits it to the cloud server. Removing noise and errors from the dust particle data through a cloud server to obtain processed dust particle data, combining the processed dust particle data with ambient air pressure data, obtaining a first data set through a Kalman filter algorithm, and storing the first data set in a predefined format; Initial parameters of a particle swarm optimization model are set via a cloud server, and the first data set is input into the particle swarm optimization model to train the particle swarm optimization model; the initial parameters include the number, velocity, and position of particles; and the particle swarm optimization model is used to generate a prediction result including a motion trend of dust particles; The output results of the particle swarm optimization model are obtained through the dust removal instrument's built-in system, and the movement trend and concentration changes of the dust particles are analyzed. The insulation status of the cable connector is obtained through the dust removal instrument's insulation status sensor. A second data set is constructed by combining the movement trend of the dust particles, the concentration changes, and the insulation status of the cable connector. The second data set is used to adjust the operating frequency and cleaning intensity of the dust removal instrument. The working intensity of the dust removal instrument is obtained through a fuzzy logic controller in the dust removal instrument; the input parameters of the fuzzy logic controller include dust movement trend, concentration change, and insulation status of cable connectors, and the output parameter is the working intensity of the dust removal instrument; the working intensity of the dust removal instrument includes voltage, current, operating frequency, vibration frequency, and wind speed; Based on the insulation state of the cable joint, it is determined whether the insulation performance of the cable joint meets the safety standard. If the insulation performance of the cable joint meets the safety standard, an instruction to perform a plugging operation on the cable joint is issued. If the insulation performance of the cable joint does not meet the safety standard, a second data set is input into a fuzzy logic controller to obtain output parameters and issue an instruction to cause a dust removal device to perform a dust removal operation according to the output parameters of the fuzzy logic controller. By analyzing the insulation state of the cable joint during dust removal, instructions to cause the dust removal device to perform a dust removal operation according to the output parameters of the fuzzy logic controller are continuously issued until the insulation performance of the cable joint meets the safety standard. By continuously monitoring the communication status between the cloud server, cable connector and dust removal instrument, the stability of data transmission is ensured and real-time plugging data during the plugging process is collected; the real-time plugging data is analyzed by the cloud server application data acquisition module to evaluate the accuracy and safety of the plugging operation; the real-time plugging data includes torque, insertion force and dust concentration.

2. The intelligent inductive cable quick connector plugging method according to claim 1, characterized in that: The environmental sensor detects dust particle data in the air in real time, records the size and concentration of the dust particles, and transmits the collected dust particle data to a cloud server via a wireless network. The environmental sensor includes an optical particle counter, a laser radar, and a camera device; the camera device is used to capture the movement path and speed of dust particles. The air pressure monitoring system detects ambient air pressure data in real time and transmits it to the cloud server, including: An optical particle counter is used to detect dust particles in the air in real time to obtain information on particle size and concentration; a laser radar is used to capture the movement path and speed of particles; and a camera is used to record visual image data of particles. The detected dust particle size, concentration, movement path and speed as well as visual image data are transmitted in real time via wireless network to the cloud server for summary processing; The detected dust particle size, concentration, movement path and movement speed, as well as visual image data are cleaned and standardized by a data preprocessing method of data cleaning and normalization, and a dust particle data model is established by a support vector machine (SVM) and a random forest algorithm; Based on the established dust particle data model, through time series analysis and regression analysis prediction methods, the changing trend of dust particle concentration in the air over a period of time in the future is predicted in real time, and the changing trend of air quality is judged; The air pressure monitoring system detects ambient air pressure data in real time and transmits the data to the cloud server; The cloud server correlates and analyzes air pressure data with dust particle data to establish a prediction model between ambient meteorological conditions and air quality; Estimate the air quality change trend in the future through meteorological forecast data.

3. The intelligent inductive cable quick connector plugging method according to claim 1, characterized in that: The method includes removing noise and errors from the dust particle data through a cloud server to obtain processed dust particle data, combining the processed dust particle data with ambient air pressure data, obtaining a first data set through a Kalman filter algorithm, and storing the first data set in a predefined format, including: The high-frequency noise and random errors in the data are removed by wavelet threshold denoising method; The signal processing module extracts features from the filtered dust particle data to obtain key feature parameters, including the concentration, particle size distribution, and movement speed of the dust particles; Real-time air pressure data is acquired through an ambient air pressure monitoring system, and the air pressure data is time-synchronized and aligned with the processed dust particle data to obtain synchronized dust particle data and air pressure data; fusing the synchronized dust particle data and air pressure data using a Kalman filter algorithm to obtain a first data set; The first data set includes the concentration, particle size distribution and movement speed of dust particles and ambient air pressure data; Organizing and packaging the first data set through a predefined data format and structure, and adding metadata and timestamp information; The first data set is stored in a document-type NoSQL database such as MongoDB.

4. The intelligent inductive cable quick connector plugging method according to claim 1, characterized in that: The initial parameters of the particle swarm optimization model are set through the cloud server, and the first data set is input into the particle swarm optimization model to train the particle swarm optimization model; the initial parameters include the number, speed and position of particles; The particle swarm optimization model is used to generate prediction results including the movement trend of dust, including: Selecting the number of particles based on the dimension, complexity, and computational resource factors of the first data set; and generating initial velocities and positions of the particles using a random function; The particle swarm optimization model evaluates the optimization performance of each particle through a fitness function; Setting a convergence condition, wherein the particle swarm optimization model iterates according to the convergence condition to obtain a prediction model for generating a prediction result including a motion trend of dust; The convergence conditions include: Set a maximum number of iterations. When the maximum number of iterations is reached, the particle swarm optimization model is considered to have converged. Setting a minimum fitness threshold, when the optimal fitness value of multiple consecutive iterations changes less than the minimum fitness threshold, it is considered that the particle swarm optimization model has converged; Setting a minimum particle position change threshold, when the particle position change of multiple consecutive iterations is less than the minimum particle position change threshold, the particle swarm optimization model is considered to have converged; If the particle swarm optimization model satisfies one or more of the three convergence conditions, the particle swarm optimization model completes the iteration to obtain a prediction model for generating a prediction result including the movement trend of dust; The prediction model is used to perform prediction analysis on the newly collected dust particle data to generate the dust movement trend in the future.

5. The intelligent inductive cable quick connector plugging method according to claim 1, characterized in that: The output results of the particle swarm optimization model are obtained through the built-in system of the dust removal instrument, and the movement trend and concentration change of the dust particles are analyzed; the insulation state of the cable joint is obtained through the insulation state sensor of the dust removal instrument; and a second data set is constructed by combining the movement trend of the dust particles, the concentration change, and the insulation state of the cable joint; The second data set is used to adjust the operating frequency and cleaning intensity of the dust removal instrument, including: The output results of the particle swarm optimization model are obtained in real time via a wireless network; the position coordinates, movement speed and direction information of dust particles at different time points, and the numerical change curve of dust concentration are obtained; Obtaining the motion data and concentration data of dust particles through analysis; correlating the motion data and concentration data of dust particles with the spatial position information of the dust removal instrument to determine the density and distribution of dust particles encountered by the dust removal instrument during future operation; Obtaining an insulation resistance value threshold range and a dielectric loss factor threshold range, monitoring the insulation resistance value and dielectric loss factor at the cable joint in real time through the insulation status sensor of the dust removal instrument, and comparing the collected insulation resistance value with a preset insulation resistance value threshold range, and comparing the collected dielectric loss factor with a preset dielectric loss factor threshold range; When the insulation resistance value exceeds the preset insulation resistance value threshold range, or when the dielectric loss factor exceeds the preset dielectric loss factor threshold range, it is determined that the insulation state is abnormal and a warning signal is triggered; Correlating the abnormal insulation state data with the dust particle movement and concentration data at the corresponding time to construct a second data set; Based on the AdaBoost algorithm, a correlation model between dust pollution and insulation abnormality was established. The probability distribution of insulation abnormality of cable joints under different dust particle concentrations and movement trends was obtained through the correlation model. Adjust the operating frequency and cleaning intensity of dust removal equipment based on the predicted dust particle concentration and the probability of abnormal insulation status; According to the model's predicted probability of insulation abnormality, the operating frequency and cleaning intensity of the dust removal equipment are divided into low, medium, and high levels. A probability threshold is preset for each level, namely the low probability threshold, the medium probability threshold, and the high probability threshold. When the predicted dust particle concentration or insulation state abnormal probability exceeds the low-level probability threshold, the operating frequency and cleaning intensity of the dust removal equipment are increased; When the predicted dust particle concentration and insulation state abnormal probability are lower than the low-level probability threshold, the operating frequency and cleaning intensity of the dust removal equipment are reduced; According to the analysis results of the correlation model, the high-risk time window of abnormal insulation status of the cable joint is predicted. Before the high-risk time window, the cable joint is dusted and cleaned according to the operating frequency and cleaning intensity of the dust removal instrument corresponding to the probability threshold level of the high-risk time window.

6. The intelligent inductive cable quick connector plugging method according to claim 1, characterized in that: The working intensity of the dust removal instrument is obtained by a fuzzy logic controller in the dust removal instrument; the input parameters of the fuzzy logic controller include dust movement trend, concentration change and insulation status of cable joints, and the output parameter is the working intensity of the dust removal instrument; the working intensity of the dust removal instrument includes voltage, current, operating frequency, vibration frequency and wind speed, including: Obtain dust particle movement trends and concentration changes as well as cable joint insulation status; The dust concentration is divided into: low dust concentration, medium dust concentration and high dust concentration; The dust movement trend is divided into: steady dust movement trend, slowly rising dust movement trend and rapidly rising dust movement trend; The cable joint insulation status is divided into: normal cable joint insulation status, slightly abnormal cable joint insulation status and seriously abnormal cable joint insulation status; According to Mamdani reasoning method, a fuzzy rule base is constructed; Through the center of gravity defuzzification method, the result of fuzzy reasoning is converted into the specific working parameters of the dust removal instrument; and an instruction is issued to make the dust removal instrument work according to the specific working parameters.

7. The intelligent inductive cable quick connector plugging method according to claim 1, characterized in that: The method comprises: judging whether the insulation performance of the cable joint meets the safety standard based on the insulation state of the cable joint; issuing an instruction to perform a plugging operation on the cable joint if the insulation performance of the cable joint meets the safety standard; inputting a second data set into a fuzzy logic controller to obtain output parameters and issuing an instruction to cause a dust removal device to perform a dust removal operation according to the output parameters of the fuzzy logic controller if the insulation performance of the cable joint does not meet the safety standard; and continuously issuing instructions to cause the dust removal device to perform a dust removal operation according to the output parameters of the fuzzy logic controller by analyzing the insulation state of the cable joint during dust removal until the insulation performance of the cable joint meets the safety standard, including: Preset the insulation status index threshold, collect the insulation resistance value and dielectric loss factor of the cable connector, and calculate the insulation status index IS: IS=0.7×(R / R0)+0.3×(tanδ0 / tanδ), Where R is the measured insulation resistance value, R0 is the insulation resistance threshold, tanδ is the measured dielectric loss factor, and tanδ0 is the dielectric loss factor threshold; When IS is greater than or equal to the insulation state index threshold, it is determined that the insulation performance of the cable joint meets the safety standard; when IS is less than the insulation state index threshold, it is determined that the insulation performance of the cable joint does not meet the safety standard; If the insulation performance of the cable connector meets the safety standard, an instruction to perform the plugging operation of the cable connector is issued; If the insulation performance of the cable joint does not meet the safety standard, the second data set is input into the fuzzy logic controller; According to Mamdani reasoning method, a fuzzy rule base is constructed; By using the center of gravity defuzzification method, the result of fuzzy reasoning is converted into the specific working parameters of the dust removal instrument; and an instruction is issued to make the dust removal instrument work according to the specific working parameters; When the insulation state index IS is greater than the insulation state index threshold for multiple consecutive times, it is determined that the insulation performance of the cable joint has reached the safety standard, and an instruction to perform the plugging operation of the cable joint is issued; Collect the insertion depth of the connector, the displacement and speed of the plugging mechanism, calculate the deviation between the actual insertion depth of the connector and the target depth, and adjust the movement of the plugging mechanism according to the deviation between the actual insertion depth and the target depth until the plugging operation of the cable connector is completed; After completing the plugging operation of the cable connector, collect the axial compression force and judge whether the required tightening degree is achieved based on the axial compression force.

8. The intelligent inductive cable quick connector plugging method according to claim 1, characterized in that: The communication status between the cloud server, cable connector and dust removal instrument is continuously monitored to ensure the stability of data transmission and collect real-time plugging data during the plugging process; the real-time plugging data is analyzed by the cloud server using a data acquisition module to evaluate the accuracy and safety of the plugging operation; the real-time plugging data includes torque, insertion force and dust concentration, including: Through the heartbeat mechanism, the communication status between the cloud server, cable connector and dust removal instrument is monitored and the round-trip delay is recorded; The token bucket algorithm is used to shape and limit the data transmission traffic between the cloud server, cable connector and dust removal equipment; the token generation rate is dynamically adjusted according to the water level of tokens passing through; When the water level of the token bucket exceeds a certain percentage for a period of time, a traffic anomaly alarm is triggered; Collect the torque, insertion force and dust concentration in the plugging environment during the plugging process as real-time plugging data; Pre-process the real-time plug-in data and compress the data through the run-length encoding algorithm; The real-time plug-in data is filtered and smoothed by the Kalman filter algorithm to obtain the plug-in data; Establishing a plugging operation evaluation model for judging the accuracy and safety of the current plugging operation through a decision tree algorithm, inputting the plugging data into the plugging operation evaluation model; judging the accuracy and safety of the current plugging operation; The plugging data is collected and clustered. The elbow method is used to evaluate different clustering numbers K to obtain the optimal clustering number. The plugging data is classified using the K-means algorithm. The number, proportion and parameter distribution status of various plugging operations are counted to generate a plugging operation quality report.

Images