Early warning and protection system for high falling of power transmission line iron tower

Through edge computing and deep learning algorithm combined with data acquisition module, the warning threshold is automatically adjusted and emergency response is carried out, which solves the inaccuracy of early warning algorithms caused by environmental complexity and equipment accuracy limitations in the existing technology, and realizes the height of transmission line towers Efficient, accurate warning and protection of the fall.

CN119068629AInactive Publication Date: 2024-12-03JIANGSU CHANGYUAN ELECTRICAL EQUIP
View PDF 0 Cites 3 Cited by

Patent Information

Application Number
CN202411268262.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-11
Publication Date
2024-12-03
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

The existing transmission line tower high fall warning and protection system has caused data acquisition errors due to complex environment and limited equipment accuracy, which affects the accuracy of the early warning algorithm.

Method used

The data acquisition module is used to monitor the tower deformation and the location of the operators in real time, and data preprocessing and model training is carried out through edge computing and deep learning algorithms, and the warning threshold is automatically adjusted, and the protection execution module is quickly responded in an emergency to build intelligent command and dispatch. The platform performs real-time monitoring and resource scheduling.

Benefits of technology

It improves the real-time and accuracy of the early warning algorithm, enhances the safety monitoring and protection capabilities of high-altitude operations, and ensures that effective protective measures are provided in complex environments.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119068629A_ABST
    Figure CN119068629A_ABST
Patent Text Reader

Abstract

The invention relates to the field of high-rise falling early warning and protection, in particular to a high-rise falling early warning and protection system for an electric transmission line iron tower. The technical problems are that in practical application of a power transmission line iron tower high-fall early warning and protection system in the prior art, due to environment and precision factors, collected data may have errors, and therefore the accuracy of an early warning algorithm is affected; according to the technical scheme, the early warning and protection system for the high falling of the power transmission line iron tower comprises a data acquisition module, a data analysis module, an early warning response module, a protection execution module and a monitoring command center, compared with the prior art, errors may exist in data collected by a power transmission line iron tower high falling early warning and protection system; according to the system, the comprehensiveness of an early warning algorithm is improved through a multi-source data fusion technology, data are trained by utilizing a machine learning algorithm and a deep learning technology, an accurate high-altitude falling early warning prediction model is constructed, the collected data are analyzed in real time, and the real-time performance and the accuracy of the early warning algorithm are improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of high-fall warning and protection, and in particular to a high-fall warning and protection system for a power transmission line iron tower. Background Art

[0002] The transmission line tower high-fall warning and protection system is a comprehensive safety management system that aims to improve the safety of high-altitude operations on transmission line towers through advanced technical means, prevent the occurrence of high-altitude falling accidents, and provide effective protection measures in emergency situations. The transmission line tower high-fall warning and protection system achieves comprehensive monitoring and effective protection of high-altitude operation safety through the coordinated work of modules such as data collection, data processing and analysis, warning release and response, protection equipment activation, and monitoring and command. The warning algorithm of the transmission line tower high-fall warning and protection system under the existing technology relies on the accuracy and completeness of data collection. However, in actual applications, due to factors such as complex environment and equipment accuracy limitations, errors may occur in the collected data, thereby affecting the accuracy of the warning algorithm. Summary of the invention

[0003] In order to overcome the problem that in the actual application of the transmission line tower fall warning and protection system under the existing technology, due to factors such as complex environment and equipment accuracy limitations, the collected data may contain errors, thereby affecting the accuracy of the warning algorithm.

[0004] The technical solution of the present invention is: a transmission line tower high-fall warning and protection system, comprising:

[0005] The data acquisition module is used to monitor the spatial displacement of the tower deformation point, the line settlement and tilt status in real time, locate the tower and the operator, and track the operator's position and status;

[0006] The data analysis module is used to pre-process and analyze data in real time using edge computing methods, and to train models using deep learning algorithms combined with big data. It automatically adjusts warning thresholds based on real-time data changes and environmental factors to meet safety requirements under different working conditions.

[0007] The early warning response module is used to issue early warning information to relevant personnel when a dangerous situation is detected, and to assess the risk level based on the early warning information and generate an emergency response plan;

[0008] The protection execution module is used to quickly lock or release the protection equipment on the tower in an emergency to respond and protect the safety of the operators;

[0009] The monitoring and command center is used to monitor the tower and the work site in real time, and is also used to build an intelligent command and dispatch platform to achieve remote real-time monitoring, resource dispatch and emergency command.

[0010] Preferably, the data acquisition module is used to monitor the spatial displacement of the deformation point of the tower, the settlement and inclination of the line in real time, and the position of the tower and the operating personnel is located, and the position and status of the operating personnel are tracked; the data analysis module uses edge computing methods to pre-process and analyze the data in real time, and uses deep learning algorithms combined with big data for model training, and automatically adjusts the warning threshold according to real-time data changes and environmental factors to adapt to safety requirements under different working conditions; when a dangerous situation is detected, the warning response module issues warning information to relevant personnel, and evaluates the risk level based on the warning information to generate an emergency response plan; in an emergency, the protection execution module executes rapid locking or release of the protective equipment on the tower to respond to and protect the safety of the operating personnel; the monitoring and command center monitors the tower and the work site in real time, and is used to build an intelligent command and dispatch platform to achieve remote real-time monitoring, resource dispatch and emergency command.

[0011] Preferably, the data acquisition module includes a sensor array unit, a GPS positioning unit and an intelligent wearable device; the sensor array unit includes an inclination sensor, an acceleration sensor, a displacement sensor and a high-definition camera, which is used to monitor the spatial displacement of the deformation point of the tower, the settlement and inclination of the line in real time; the GPS positioning unit is used to adopt Beidou and GPS dual-mode positioning technology to improve the accuracy and reliability of geographic location information, especially the positioning capability in complex environments; the intelligent wearable device is a wearable device equipped for high-altitude workers with integrated vital signs monitoring, posture recognition and emergency call functions, which is used to track their health status and safety status in real time.

[0012] Preferably, the data acquisition module comprises the following steps when working:

[0013] S101: Start the system, execute the self-test program, and check the hardware connection status of all sensors, cameras, positioning devices, and smart wearable devices;

[0014] S102: Loading the software program of the data acquisition module, including data acquisition algorithm, data preprocessing algorithm, and encryption algorithm;

[0015] S103: Configure data acquisition parameters, including sampling frequency, data format, and storage path;

[0016] S104: Calibrate high-precision sensors to ensure the accuracy of measurement data, including zero point calibration and sensitivity adjustment of inclination sensors, acceleration sensors, displacement sensors, etc.;

[0017] S105: starting the sensor to collect data according to the preset sampling frequency;

[0018] S106: Start the camera to capture video images of the tower and the work site, and ensure that the video stream transmission is stable;

[0019] S107: acquiring raw data from sensors and cameras in real time, including physical quantity measurement values ​​and video frames; and temporarily storing the data in local storage of the edge computing device;

[0020] S108: Add accurate timestamps to each data point to ensure the time sequence and synchronization of the data;

[0021] S109: Transmit the data to the data analysis module.

[0022] Preferably, the data analysis module includes an edge computing unit, a deep learning optimization algorithm unit and a threshold adjustment unit; the edge computing unit is used for preliminary data preprocessing and real-time analysis to reduce data transmission delays; the deep learning optimization algorithm unit uses convolutional neural network CNN and long short-term memory network LSTM model combined with big data for model training to improve the accuracy and predictive ability of the early warning algorithm; the threshold adjustment unit is used to automatically adjust the early warning threshold according to real-time data changes and environmental factors to adapt to safety requirements under different working conditions.

[0023] Preferably, the data analysis module comprises the following steps when working:

[0024] S201: receiving a real-time transmitted data packet from a data acquisition module, including sensor data, positioning information, and smart wearable device data;

[0025] S202: Perform data integrity check to check the timestamp and sequence number of the data to ensure the timing and continuity of the data;

[0026] S203: preprocessing the received raw data, including data cleaning, denoising, filtering and compression;

[0027] S204: After the data preprocessing is completed, extract key features from the cleaned and filtered data;

[0028] S205: For the tilt sensor data, frequency features are extracted using Fourier transform to identify the vibration mode of the tower; for the acceleration sensor, the shaking degree of the tower is evaluated by calculating the root mean square value of the acceleration;

[0029] S206: extracting features from the video frames using a convolutional neural network (CNN). After the video data is processed by the CNN, a series of feature maps are obtained, which represent different visual features of the tower and identify deformation or abnormal behavior of the tower structure.

[0030] S207: extracting physiological state characteristics of the wearer through a heart rate variability analysis HRV algorithm to assess the wearer's health status and workload;

[0031] S208: Fusing feature parameters from different sensors and devices to form a comprehensive feature vector; directly concatenating feature vectors from different sources into a longer vector, assigning different weights according to the importance of the features, and then performing weighted summation, and using an autoencoder to fuse the relationship between the features;

[0032] S209: Select the long short-term memory network LSTM as the prediction model;

[0033] S210: Use historical data and some real-time data to train the LSTM model, taking the feature vector as input and the safety status of the tower as the output label;

[0034] S211: Build an LSTM network structure, including an input layer, multiple LSTM layers, a fully connected layer, and an output layer;

[0035] S212: Use back propagation algorithm and gradient descent method to adjust model parameters and minimize prediction error;

[0036] S213: Receive and process sensor and video data in real time, extract features to form feature vectors, and input the real-time data into the trained LSTM model for prediction;

[0037] S214: Input the feature vector into the LSTM model to obtain the prediction result of the current safety status of the tower;

[0038] S215: Set initial warning thresholds based on historical data and expert experience;

[0039] S216: Using support vector machine SVM as a dynamic adjustment algorithm;

[0040] S217: Continuously monitor the tower’s real-time data and environmental factors;

[0041] S218: Using real-time data and environmental factors as input features to construct a feature vector;

[0042] S219: Use the SVM model to dynamically adjust the warning threshold according to the change of the feature vector. When the SVM model predicts that the safety status of the tower is about to deteriorate, the warning threshold is lowered in advance to improve the response speed.

[0043] Preferably, the early warning response module includes an early warning release unit and an emergency response unit; the early warning release unit is used to release early warning information to relevant personnel through sound and light alarms, text messages, APP push, etc. when a dangerous situation is detected; the emergency response unit is used to formulate emergency plans to ensure that a rapid response can be made after receiving the early warning information and effective measures can be taken to reduce risks.

[0044] Preferably, the early warning response module comprises the following steps when working:

[0045] S301: Continuously monitor the prediction results output by the data processing and analysis module, and whether the real-time data reaches or exceeds a preset warning threshold;

[0046] S302: By comparing the real-time data with the threshold through the set algorithm logic, when the warning condition is triggered, the next step is entered;

[0047] S303: Determine the warning level according to the type, severity and historical data of the condition that triggers the warning;

[0048] S304: Using a risk assessment model, taking into account multiple factors, and deriving a warning level through weighted summation and machine learning algorithms;

[0049] S305: Select and start a corresponding warning information release channel according to the determined warning level;

[0050] S306: Select the most suitable warning information release method according to the preset priority and actual situation;

[0051] S307: Encode the warning information into a format suitable for transmission through various channels, and transmit it to the receiving end through the corresponding communication protocol; if no confirmation receipt is received within a certain period of time, start the timeout retransmission mechanism to ensure that the warning information is not missed;

[0052] S308: After receiving the warning information, the receiving end sends a confirmation receipt to the system;

[0053] S309: After the warning information is released, the corresponding emergency response process is initiated according to the warning level and the preset emergency response plan;

[0054] S310: Use AI-assisted decision-making models to conduct risk assessments based on early warning information and actual on-site conditions, and generate the best emergency response plan based on big data;

[0055] S311: Convert the emergency response plan into specific emergency instructions and distribute them to relevant personnel through communication channels for execution.

[0056] Preferably, the protection execution module includes protection equipment, an automatic sensing unit, an automatic locking unit and an intelligent release unit; the automatic sensing unit, the automatic locking unit and the intelligent release unit are all arranged in the protection equipment, and the protection equipment is arranged at the construction site of the transmission line tower. Through the automatic sensing unit, the automatic locking unit and the intelligent release unit, the emergency command signal can be quickly received in an emergency situation, and relevant protection operations can be executed in response to protect the safety of the operating personnel.

[0057] Preferably, the protection execution module includes the following steps when working:

[0058] S401: When the system starts, the protection execution module performs initialization settings, including checking the device hardware connection status, power supply status, and sensor calibration;

[0059] S402: The protective device receives status information from the data acquisition module by wireless or wired means, including the tower tilt angle, acceleration, displacement, and vital signs and posture of the high-altitude workers;

[0060] S403: Based on the real-time monitored status parameters, a risk assessment is performed to determine whether there is a risk of falling from a height; if the assessment result is a high risk, an early warning mechanism is triggered;

[0061] S404: When the warning signal is triggered, the protective equipment starts and executes corresponding protective measures, such as automatic locking and intelligent release, to protect the safety of high-altitude workers;

[0062] S405: After the protective device is started and protective measures are executed, the protective effect is evaluated, and the subsequent protective strategy is adjusted and optimized according to the evaluation results.

[0063] Preferably, the monitoring and command center includes a high-definition monitoring unit and a command and dispatch platform; the high-definition monitoring unit uses high-definition panoramic cameras and 3D modeling methods to monitor the tower and the work site in all directions and from multiple angles; the command and dispatch platform integrates GIS geographic information system, big data analysis technology and AI-assisted decision-making system to build an intelligent command and dispatch platform to achieve remote real-time monitoring, resource dispatch and emergency command.

[0064] Beneficial effects of the present invention:

[0065] 1. Compared with the existing transmission line tower high-fall warning and protection system, the warning algorithm relies on the accuracy and completeness of data collection. However, in actual applications, due to factors such as complex environment and equipment accuracy limitations, the collected data may contain errors, thus affecting the accuracy of the warning algorithm. This system uses multi-source data fusion technology to improve the comprehensiveness of the warning algorithm, uses machine learning algorithms and deep learning technologies to train data, builds an accurate high-fall warning prediction model, and conducts real-time analysis of the collected data to improve the real-time and accuracy of the warning algorithm.

[0066] 2. Receive the real-time transmitted data packets from the data acquisition module through the data analysis module, including sensor data, positioning information, and smart wearable device data; pre-process the received raw data; extract key features from the cleaned and filtered data after data pre-processing; for the tilt sensor data, use Fourier transform to extract frequency features to identify the vibration mode of the tower; for the acceleration sensor, evaluate the shaking degree of the tower by calculating the root mean square value of the acceleration; use the convolutional neural network CNN to extract features from the video frames. After the video data is processed by CNN, a series of feature maps are obtained to represent the different visual features of the tower and identify the deformation or abnormal behavior of the tower structure; extract the physiological state characteristics of the wearer through the heart rate variability analysis HRV algorithm to evaluate their health status and workload; fuse the feature parameters from different sensors and devices to form a comprehensive feature vector; directly splice the feature vectors from different sources into a longer vector, give different weights according to the importance of the features, and then perform weighted summation, and use the autoencoder to fuse the relationship between the features; improve the comprehensiveness of the early warning algorithm through multi-source data fusion technology;

[0067] 3. Select the long short-term memory network LSTM as the prediction model; use historical data and some real-time data to train the LSTM model, use the feature vector as input, and the safety status of the tower as the output label; build the LSTM network structure, including the input layer, multiple LSTM layers, fully connected layer and output layer; use the back propagation algorithm and gradient descent method to adjust the model parameters to minimize the prediction error; receive and process sensor and video data in real time, extract features to form feature vectors, and input real-time data into the trained LSTM model for prediction; input the feature vector into the LSTM model to obtain the prediction of the current safety status of the tower Results: Set the initial warning threshold based on historical data and expert experience; use support vector machine (SVM) as a dynamic adjustment algorithm; continuously monitor the real-time data and environmental factors of the tower; use real-time data and environmental factors as input features to construct feature vectors; use the SVM model to dynamically adjust the warning threshold according to the changes in the feature vector. When the SVM model predicts that the safety status of the tower is about to deteriorate, lower the warning threshold in advance to increase the response speed; thus, use machine learning algorithms and deep learning technology to train data, build an accurate high-fall warning prediction model, and conduct real-time analysis of the collected data to improve the real-time and accuracy of the warning algorithm. A crushing and rolling device for silt and fly ash roadbed filling in a narrow space BRIEF DESCRIPTION OF THE DRAWINGS

[0068] Figure 1 Shown is a schematic diagram of the working process of the power transmission line tower high-fall warning and protection system of the present invention;

[0069] Figure 2 Shown is a schematic diagram of the working process of the data analysis module of the power transmission line tower high-fall warning and protection system of the present invention. DETAILED DESCRIPTION

[0070] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0071] See also Figure 1-2 The present invention provides an embodiment: a transmission line tower high-fall warning and protection system, comprising:

[0072] The data acquisition module is used to monitor the spatial displacement of the tower deformation point, the line settlement and tilt status in real time, locate the tower and the operator, and track the operator's position and status;

[0073] The data analysis module is used to pre-process and analyze data in real time using edge computing methods, and to train models using deep learning algorithms combined with big data. It automatically adjusts warning thresholds based on real-time data changes and environmental factors to meet safety requirements under different working conditions.

[0074] The early warning response module is used to issue early warning information to relevant personnel when a dangerous situation is detected, and to assess the risk level based on the early warning information and generate an emergency response plan;

[0075] The protection execution module is used to quickly lock or release the protection equipment on the tower in an emergency to respond and protect the safety of the operators;

[0076] The monitoring and command center is used to monitor the tower and the work site in real time, and is also used to build an intelligent command and dispatch platform to achieve remote real-time monitoring, resource dispatch and emergency command.

[0077] Preferably, the data acquisition module is used to monitor the spatial displacement of the deformation point of the tower, the settlement and inclination of the line in real time, and the position of the tower and the operating personnel is located, and the position and status of the operating personnel are tracked; the data analysis module uses edge computing methods to pre-process and analyze the data in real time, and uses deep learning algorithms combined with big data for model training, and automatically adjusts the warning threshold according to real-time data changes and environmental factors to adapt to safety requirements under different working conditions; when a dangerous situation is detected, the warning response module issues warning information to relevant personnel, and evaluates the risk level based on the warning information to generate an emergency response plan; in an emergency, the protection execution module executes rapid locking or release of the protective equipment on the tower to respond to and protect the safety of the operating personnel; the monitoring and command center monitors the tower and the work site in real time, and is used to build an intelligent command and dispatch platform to achieve remote real-time monitoring, resource dispatch and emergency command.

[0078] Preferably, the data acquisition module includes a sensor array unit, a GPS positioning unit and an intelligent wearable device; the sensor array unit includes an inclination sensor, an acceleration sensor, a displacement sensor and a high-definition camera, which is used to monitor the spatial displacement of the deformation point of the tower, the settlement and inclination of the line in real time; the GPS positioning unit is used to adopt Beidou and GPS dual-mode positioning technology to improve the accuracy and reliability of geographic location information, especially the positioning capability in complex environments; the intelligent wearable device is a wearable device equipped for high-altitude workers with integrated vital signs monitoring, posture recognition and emergency call functions, which is used to track their health status and safety status in real time.

[0079] Preferably, the data acquisition module comprises the following steps when working:

[0080] S101: Start the system, execute the self-test program, and check the hardware connection status of all sensors, cameras, positioning devices, and smart wearable devices;

[0081] S102: Loading the software program of the data acquisition module, including data acquisition algorithm, data preprocessing algorithm, and encryption algorithm;

[0082] S103: Configure data acquisition parameters, including sampling frequency, data format, and storage path;

[0083] S104: Calibrate high-precision sensors to ensure the accuracy of measurement data, including zero point calibration and sensitivity adjustment of inclination sensors, acceleration sensors, displacement sensors, etc.;

[0084] S105: starting the sensor to collect data according to the preset sampling frequency;

[0085] S106: Start the camera to capture video images of the tower and the work site, and ensure that the video stream transmission is stable;

[0086] S107: acquiring raw data from sensors and cameras in real time, including physical quantity measurement values ​​and video frames; and temporarily storing the data in local storage of the edge computing device;

[0087] S108: Add accurate timestamps to each data point to ensure the time sequence and synchronization of the data;

[0088] S109: Transmit the data to the data analysis module.

[0089] Preferably, the data analysis module includes an edge computing unit, a deep learning optimization algorithm unit and a threshold adjustment unit; the edge computing unit is used for preliminary data preprocessing and real-time analysis to reduce data transmission delays; the deep learning optimization algorithm unit uses convolutional neural network CNN and long short-term memory network LSTM model combined with big data for model training to improve the accuracy and predictive ability of the early warning algorithm; the threshold adjustment unit is used to automatically adjust the early warning threshold according to real-time data changes and environmental factors to adapt to safety requirements under different working conditions.

[0090] Preferably, the data analysis module comprises the following steps when working:

[0091] S201: receiving a real-time transmitted data packet from a data acquisition module, including sensor data, positioning information, and smart wearable device data;

[0092] S202: Perform data integrity check to check the timestamp and sequence number of the data to ensure the timing and continuity of the data;

[0093] S203: preprocessing the received raw data, including data cleaning, denoising, filtering and compression;

[0094] S204: After the data preprocessing is completed, extract key features from the cleaned and filtered data;

[0095] S205: For the tilt sensor data, frequency features are extracted using Fourier transform to identify the vibration mode of the tower; for the acceleration sensor, the shaking degree of the tower is evaluated by calculating the root mean square value of the acceleration;

[0096] S206: extracting features from the video frames using a convolutional neural network (CNN). After the video data is processed by the CNN, a series of feature maps are obtained, which represent different visual features of the tower and identify deformation or abnormal behavior of the tower structure.

[0097] S207: extracting physiological state characteristics of the wearer through a heart rate variability analysis HRV algorithm to assess the wearer's health status and workload;

[0098] S208: Fusing feature parameters from different sensors and devices to form a comprehensive feature vector; directly concatenating feature vectors from different sources into a longer vector, assigning different weights according to the importance of the features, and then performing weighted summation, and using an autoencoder to fuse the relationship between the features;

[0099] S209: Select the long short-term memory network LSTM as the prediction model;

[0100] S210: Use historical data and some real-time data to train the LSTM model, taking the feature vector as input and the safety status of the tower as the output label;

[0101] S211: Build an LSTM network structure, including an input layer, multiple LSTM layers, a fully connected layer, and an output layer;

[0102] S212: Use back propagation algorithm and gradient descent method to adjust model parameters and minimize prediction error;

[0103] S213: Receive and process sensor and video data in real time, extract features to form feature vectors, and input the real-time data into the trained LSTM model for prediction;

[0104] S214: Input the feature vector into the LSTM model to obtain the prediction result of the current safety status of the tower;

[0105] S215: Set initial warning thresholds based on historical data and expert experience;

[0106] S216: Using support vector machine SVM as a dynamic adjustment algorithm;

[0107] S217: Continuously monitor the tower’s real-time data and environmental factors;

[0108] S218: Using real-time data and environmental factors as input features to construct a feature vector;

[0109] S219: Use the SVM model to dynamically adjust the warning threshold according to the change of the feature vector. When the SVM model predicts that the safety status of the tower is about to deteriorate, the warning threshold is lowered in advance to improve the response speed.

[0110] Preferably, the early warning response module includes an early warning release unit and an emergency response unit; the early warning release unit is used to release early warning information to relevant personnel through sound and light alarms, text messages, APP push, etc. when a dangerous situation is detected; the emergency response unit is used to formulate emergency plans to ensure that a rapid response can be made after receiving the early warning information and effective measures can be taken to reduce risks.

[0111] Preferably, the early warning response module comprises the following steps when working:

[0112] S301: Continuously monitor the prediction results output by the data processing and analysis module, and whether the real-time data reaches or exceeds a preset warning threshold;

[0113] S302: By comparing the real-time data with the threshold through the set algorithm logic, when the warning condition is triggered, the next step is entered;

[0114] S303: Determine the warning level according to the type, severity and historical data of the condition that triggers the warning;

[0115] S304: Using a risk assessment model, taking into account multiple factors, and deriving a warning level through weighted summation and machine learning algorithms;

[0116] S305: Select and start a corresponding warning information release channel according to the determined warning level;

[0117] S306: Select the most suitable warning information release method according to the preset priority and actual situation;

[0118] S307: Encode the warning information into a format suitable for transmission through various channels, and transmit it to the receiving end through the corresponding communication protocol; if no confirmation receipt is received within a certain period of time, start the timeout retransmission mechanism to ensure that the warning information is not missed;

[0119] S308: After receiving the warning information, the receiving end sends a confirmation receipt to the system;

[0120] S309: After the warning information is released, the corresponding emergency response process is initiated according to the warning level and the preset emergency response plan;

[0121] S310: Use AI-assisted decision-making models to conduct risk assessments based on early warning information and actual on-site conditions, and generate the best emergency response plan based on big data;

[0122] S311: Convert the emergency response plan into specific emergency instructions and distribute them to relevant personnel through communication channels for execution.

[0123] Preferably, the protection execution module includes protection equipment, an automatic sensing unit, an automatic locking unit and an intelligent release unit; the automatic sensing unit, the automatic locking unit and the intelligent release unit are all arranged in the protection equipment, and the protection equipment is arranged at the construction site of the transmission line tower. Through the automatic sensing unit, the automatic locking unit and the intelligent release unit, the emergency command signal can be quickly received in an emergency situation, and relevant protection operations can be executed in response to protect the safety of the operating personnel.

[0124] Preferably, the protection execution module includes the following steps when working:

[0125] S401: When the system starts, the protection execution module performs initialization settings, including checking the device hardware connection status, power supply status, and sensor calibration;

[0126] S402: The protective device receives status information from the data acquisition module by wireless or wired means, including the tower tilt angle, acceleration, displacement, and vital signs and posture of the high-altitude workers;

[0127] S403: Based on the real-time monitored status parameters, a risk assessment is performed to determine whether there is a risk of falling from a height; if the assessment result is a high risk, an early warning mechanism is triggered;

[0128] S404: When the warning signal is triggered, the protective equipment starts and executes corresponding protective measures, such as automatic locking and intelligent release, to protect the safety of high-altitude workers;

[0129] S405: After the protective device is started and protective measures are executed, the protective effect is evaluated, and the subsequent protective strategy is adjusted and optimized according to the evaluation results.

[0130] Preferably, the monitoring and command center includes a high-definition monitoring unit and a command and dispatch platform; the high-definition monitoring unit uses high-definition panoramic cameras and 3D modeling methods to monitor the tower and the work site in all directions and from multiple angles; the command and dispatch platform integrates GIS geographic information system, big data analysis technology and AI-assisted decision-making system to build an intelligent command and dispatch platform to achieve remote real-time monitoring, resource dispatch and emergency command.

[0131] The embodiments of the present invention are described in detail above with reference to the accompanying drawings, but the present invention is not limited to the above embodiments, and various changes can be made within the knowledge scope of those skilled in the art without departing from the spirit of the present invention.

Claims

1. A transmission line tower high-fall warning and protection system, Features: Included are: The data acquisition module is used to monitor the spatial displacement of the tower deformation point, the line settlement and tilt status in real time, locate the tower and the operator, and track the operator's position and status; The data analysis module is used to pre-process and analyze data in real time using edge computing methods, and to train models using deep learning algorithms combined with big data. It automatically adjusts warning thresholds based on real-time data changes and environmental factors to meet safety requirements under different working conditions. The early warning response module is used to issue early warning information to relevant personnel when a dangerous situation is detected, and to assess the risk level based on the early warning information and generate an emergency response plan; The protection execution module is used to quickly lock or release the protection equipment on the tower in an emergency to respond and protect the safety of the operators; The monitoring and command center is used to monitor the tower and the work site in real time, and is also used to build an intelligent command and dispatch platform to achieve remote real-time monitoring, resource dispatch and emergency command.

2. A transmission line tower high-fall warning and protection system according to claim 1, Features: The data acquisition module includes a sensor array unit, a GPS positioning unit and an intelligent wearable device; the sensor array unit includes an inclination sensor, an acceleration sensor, a displacement sensor and a high-definition camera, which are used to monitor the spatial displacement of the tower deformation point, line settlement and tilt status in real time; the GPS positioning unit is used to adopt Beidou and GPS dual-mode positioning technology to improve the accuracy and reliability of geographic location information, especially the positioning capability in complex environments; the intelligent wearable device is a wearable device equipped for high-altitude workers with integrated vital signs monitoring, posture recognition and emergency call functions, which is used to track their health status and safety status in real time.

3. A transmission line tower fall warning and protection system according to claim 2, Features: When the data acquisition module is working, it includes the following steps: S101: Start the system, execute the self-test program, and check the hardware connection status of all sensors, cameras, positioning devices, and smart wearable devices; S102: Loading the software program of the data acquisition module, including data acquisition algorithm, data preprocessing algorithm, and encryption algorithm; S103: Configure data acquisition parameters, including sampling frequency, data format, and storage path; S104: Calibrate high-precision sensors to ensure the accuracy of measurement data, including zero point calibration and sensitivity adjustment of inclination sensors, acceleration sensors, displacement sensors, etc.; S105: starting the sensor to collect data according to the preset sampling frequency; S106: Start the camera to capture video images of the tower and the work site, and ensure that the video stream transmission is stable; S107: acquiring raw data from sensors and cameras in real time, including physical quantity measurement values ​​and video frames; and temporarily storing the data in local storage of the edge computing device; S108: Add accurate timestamps to each data point to ensure the time sequence and synchronization of the data; S109: Transmit the data to the data analysis module.

4. A transmission line tower fall warning and protection system according to claim 3, Features: The data analysis module includes an edge computing unit, a deep learning optimization algorithm unit and a threshold adjustment unit; the edge computing unit is used for preliminary data preprocessing and real-time analysis to reduce data transmission delays; the deep learning optimization algorithm unit uses convolutional neural network CNN and long short-term memory network LSTM model combined with big data for model training to improve the accuracy and predictive ability of the early warning algorithm; the threshold adjustment unit is used to automatically adjust the early warning threshold according to real-time data changes and environmental factors to adapt to safety requirements under different working conditions.

5. A transmission line tower high-fall warning and protection system according to claim 4, Features: When the data analysis module is working, it includes the following steps: S201: receiving a real-time transmitted data packet from a data acquisition module, including sensor data, positioning information, and smart wearable device data; S202: Perform data integrity check to check the timestamp and sequence number of the data to ensure the timing and continuity of the data; S203: preprocessing the received raw data, including data cleaning, denoising, filtering and compression; S204: After the data preprocessing is completed, extract key features from the cleaned and filtered data; S205: For the tilt sensor data, frequency features are extracted using Fourier transform to identify the vibration mode of the tower; for the acceleration sensor, the shaking degree of the tower is evaluated by calculating the root mean square value of the acceleration; S206: extracting features from the video frames using a convolutional neural network (CNN). After the video data is processed by the CNN, a series of feature maps are obtained, which represent different visual features of the tower and identify deformation or abnormal behavior of the tower structure. S207: extracting physiological state characteristics of the wearer through a heart rate variability analysis HRV algorithm to assess the wearer's health status and workload; S208: Fusing feature parameters from different sensors and devices to form a comprehensive feature vector; directly concatenating feature vectors from different sources into a longer vector, assigning different weights according to the importance of the features, and then performing weighted summation, and using an autoencoder to fuse the relationship between the features; S209: Select the long short-term memory network LSTM as the prediction model; S210: Use historical data and some real-time data to train the LSTM model, taking the feature vector as input and the safety status of the tower as the output label; S211: Build an LSTM network structure, including an input layer, multiple LSTM layers, a fully connected layer, and an output layer; S212: Use back propagation algorithm and gradient descent method to adjust model parameters and minimize prediction error; S213: Receive and process sensor and video data in real time, extract features to form feature vectors, and input the real-time data into the trained LSTM model for prediction; S214: Input the feature vector into the LSTM model to obtain the prediction result of the current safety status of the tower; S215: Set initial warning thresholds based on historical data and expert experience; S216: Using support vector machine SVM as a dynamic adjustment algorithm; S217: Continuously monitor the tower’s real-time data and environmental factors; S218: Using real-time data and environmental factors as input features to construct a feature vector; S219: Use the SVM model to dynamically adjust the warning threshold according to the change of the feature vector. When the SVM model predicts that the safety status of the tower is about to deteriorate, the warning threshold is lowered in advance to improve the response speed.

6. A transmission line tower fall warning and protection system according to claim 5, Features: The early warning response module includes an early warning release unit and an emergency response unit; the early warning release unit is used to release early warning information to relevant personnel through sound and light alarms, text messages, APP push, etc. when a dangerous situation is detected; the emergency response unit is used to formulate emergency plans to ensure that a rapid response can be made after receiving the early warning information and effective measures can be taken to reduce risks.

7. A transmission line tower fall warning and protection system according to claim 6, Features: When the early warning response module is working, it includes the following steps: S301: Continuously monitor the prediction results output by the data processing and analysis module, and whether the real-time data reaches or exceeds a preset warning threshold; S302: By comparing the real-time data with the threshold through the set algorithm logic, when the warning condition is triggered, the next step is entered; S303: Determine the warning level according to the type, severity and historical data of the condition that triggers the warning; S304: Using a risk assessment model, taking into account multiple factors, and deriving a warning level through weighted summation and machine learning algorithms; S305: Select and start a corresponding warning information release channel according to the determined warning level; S306: Select the most suitable warning information release method according to the preset priority and actual situation; S307: Encode the warning information into a format suitable for transmission through various channels, and transmit it to the receiving end through the corresponding communication protocol; if no confirmation receipt is received within a certain period of time, start the timeout retransmission mechanism to ensure that the warning information is not missed; S308: After receiving the warning information, the receiving end sends a confirmation receipt to the system; S309: After the warning information is released, the corresponding emergency response process is initiated according to the warning level and the preset emergency response plan; S310: Use AI-assisted decision-making models to conduct risk assessments based on early warning information and actual on-site conditions, and generate the best emergency response plan based on big data; S311: Convert the emergency response plan into specific emergency instructions and distribute them to relevant personnel through communication channels for execution.

8. A transmission line tower fall warning and protection system according to claim 7, Features: The protection execution module includes protection equipment, an automatic sensing unit, an automatic locking unit and an intelligent release unit; the automatic sensing unit, the automatic locking unit and the intelligent release unit are all arranged in the protection equipment, and the protection equipment is arranged at the construction site of the transmission line tower. Through the automatic sensing unit, the automatic locking unit and the intelligent release unit, the emergency command signal can be quickly received in an emergency, and relevant protection operations can be executed in response to protect the safety of the operating personnel.

9. A transmission line tower fall warning and protection system according to claim 8, Features: When the protection execution module is working, it includes the following steps: S401: When the system starts, the protection execution module performs initialization settings, including checking the device hardware connection status, power supply status, and sensor calibration; S402: The protective device receives status information from the data acquisition module by wireless or wired means, including the tower tilt angle, acceleration, displacement, and vital signs and posture of the high-altitude workers; S403: Based on the real-time monitored status parameters, a risk assessment is performed to determine whether there is a risk of falling from a height; if the assessment result is a high risk, an early warning mechanism is triggered; S404: When the warning signal is triggered, the protective equipment starts and executes corresponding protective measures, such as automatic locking and intelligent release, to protect the safety of high-altitude workers; S405: After the protective device is started and protective measures are executed, the protective effect is evaluated, and the subsequent protective strategy is adjusted and optimized according to the evaluation results.

10. A transmission line tower high-fall warning and protection system according to claim 9, Features: The monitoring and command center includes a high-definition monitoring unit and a command and dispatch platform; the high-definition monitoring unit uses high-definition panoramic cameras and 3D modeling methods to monitor the tower and the work site in all directions and from multiple angles; the command and dispatch platform integrates GIS geographic information system, big data analysis technology and AI-assisted decision-making system to build an intelligent command and dispatch platform to achieve remote real-time monitoring, resource dispatch and emergency command.

Citation Information

Cited By

  • Power transmission line monitoring method based on edge calculation

    CN119693186A

  • Iron tower detection and early warning system based on convolutional neural network

    CN120510690A

  • Falling protector safety control method and system based on collision self-inspection and multidirectional locking

    CN120891762A