Geological disaster pre-judging device and method thereof

Abstract

The invention discloses a geological disaster pre-judgment device and method, and the device comprises an acquisition unit which is used for collecting the inclination angle, acceleration and soil humidity signals of a to-be-monitored power transmission line tower; the wireless transceiver module is used for receiving the data acquired by the acquisition unit; the control unit is used for processing and analyzing the collected data and obtaining geological disaster pre-judgment data; the storage module is used for receiving and storing the collected data and geological disaster pre-judgment data; a communication module; and the sending module is used for sending the geological disaster pre-judgment data to the user terminal. Diversified transmission line tower operation data can be obtained, in cooperation with the neural network algorithm model, deep mining of the data is facilitated, and the accuracy of prejudging geological disasters is practically improved. The operation state of the power transmission line tower is accurately monitored in real time by using hardware with low cost and low power consumption, and geological disasters which may occur are accurately predicted by using obtained data.

Description

Technical Field

[0001] The present invention relates to the field of power system operation monitoring, and particularly to a geological disaster prediction device and method based on transmission line tower monitoring. Background Art

[0002] Transmission lines are long, and the projects often cross different topographic and geomorphic units, regional geological structure units, hydrogeological units, engineering geological units, and mining areas. The siting design of the towers is limited by the depth of preliminary exploration and construction transportation conditions. Some may be very close to the disaster points or have been on the geological disaster surface due to human activities in recent years. For transmission lines, the geological disasters that are likely to occur due to special topographic and geological conditions mainly include small landslides, collapses, mined-out area subsidence, ground fissures, etc. They have the distinct characteristics of long development time, unobvious process, strong suddenness, large destructiveness, and difficulty in prevention and control. Their direct harm is that the tower collapse leads to grounding accidents or wire breakage accidents, thus causing heavy losses to the power grid and the national economy. Especially in recent years, with the increase in extreme weather and the deterioration of the environment, the damage caused by human activities is becoming increasingly frequent, and more and more events are continuously endangering the safe operation of transmission lines. Therefore, it is very important to predict possible geological disasters through the daily monitoring of the operation of transmission line towers. Currently, for the daily monitoring of the operation of transmission line towers, handheld monitoring instruments are generally used. The handheld monitoring instruments can measure the inclination degree of the towers irregularly, but they cannot obtain real-time and accurate data of the collected displacement, so they cannot predict geological disasters, and the obtained data are all after the event, unable to monitor and predict the operation state of the iron towers in real time. Some poles are also installed with satellite positioning systems, but they cannot monitor deformation factors and accurately locate small displacements. In addition, the previous positioning system has high hardware costs and high power consumption, which is not conducive to large-scale promotion. In addition, the current geological disaster prediction methods based on transmission line tower monitoring are often limited by the problem of single monitoring data, unable to deeply mine the obtained data, and unable to meet the requirements of accurate prediction of geological disasters. Summary of the Invention

[0003] To solve the above problems, on the one hand, the present invention provides a geological disaster prediction device, including a power supply unit and a user terminal, characterized in that it further includes:

[0004] A collection unit for collecting the inclination angle signal, acceleration signal of the transmission line tower to be monitored, and the soil humidity signal of the location where the transmission line tower to be monitored is located;

[0005] A wireless transceiver module for receiving the data collected by the collection unit;

[0006] A control unit for processing and analyzing the collected data received by the wireless transceiver module and obtaining geological disaster prediction data;

[0007] A storage module for receiving and storing the collected data sent by the wireless transceiver module and the geological disaster prediction data obtained by the control unit;

[0008] A communication module for sending the geological disaster prediction data obtained by the control unit to the user terminal.

[0009] Further, the collection unit includes a three-axis inclinometer, a three-axis accelerometer, and a soil moisture sensor. The three-axis inclinometer and the three-axis accelerometer are placed at the top of the transmission line tower to be monitored, and the soil moisture sensor is placed below the ground surface at the location of the transmission line tower to be monitored.

[0010] Further, the control unit, the wireless transceiver module, the storage module, and the communication module are placed in the middle and lower parts of the transmission line tower to be monitored.

[0011] Further, the control unit includes a data preprocessing module, a neural network model, and a data analysis module. The data preprocessing module preprocesses the collected data transmitted by the wireless transceiver module. The neural network model is used to obtain a prediction curve based on the preprocessed data and the historical data of the transmission line towers where geological disasters have occurred to obtain a standard curve. The data analysis module is used to compare the prediction curve with the standard curve obtained from the historical data to obtain geological disaster prediction data.

[0012] Further, the three-axis accelerometer is an ADXL355 three-axis accelerometer.

[0013] A method for predicting geological disasters using the geological disaster prediction device as described above includes:

[0014] Using the collection unit to collect the inclination angle signal, acceleration signal of the transmission line tower to be monitored, and the soil moisture signal at the location of the transmission line tower to be monitored;

[0015] Converting the collected acceleration signal into a displacement signal;

[0016] Preprocessing the obtained inclination angle signal, displacement signal, and soil moisture signal;

[0017] Using the preprocessed inclination angle signal, displacement signal, and soil moisture signal as feature vectors to input into the neural network model to obtain a prediction curve;

[0018] Obtaining the inclination angle signal, acceleration signal, and soil moisture signal of the transmission line towers where geological disasters have occurred from the historical data of the transmission line tower detection to obtain a standard curve;

[0019] Calculate the similarity between the obtained prediction curve and the standard curve to obtain the geological disaster pre-judgment data. The greater the similarity, the greater the possibility of a geological disaster occurring;

[0020] Send the obtained geological disaster pre-judgment data to the user terminal.

[0021] Furthermore, in the acquisition unit, the triaxial inclination sensor acquires the inclination angle signal of the transmission line tower to be monitored, the triaxial acceleration sensor acquires the acceleration signal of the transmission line tower to be monitored, and the soil humidity sensor acquires the soil humidity signal at the location of the transmission line tower to be monitored.

[0022] Furthermore, the process of converting the acceleration signal collected by the triaxial acceleration sensor into a displacement signal is to perform high-speed acquisition on the original acceleration signal, perform Fourier transform to convert it into the frequency domain space, perform two integral operations on the signal in the frequency domain, and then convert the integral result into a time-domain displacement signal through inverse Fourier transform.

[0023] Furthermore, the number of hidden layers of the neural network is 15. The activation function of each node neuron in the neural network is calculated using the Sigmoid function and normalized to between -1 and 1. The weight correction of the neural network can adopt the gradient descent method or the conjugate gradient method. The weight correction formula is as follows:

[0024] W(k + 1) = W(k) + ΔW(k)

[0025] Where: W(k + 1) and W(k) are the connection weights of adjacent training numbers between each layer of nodes in the neural network, ΔW(k) is the correction value of the weight, and k is the number of training times.

[0026] Furthermore, the dynamic time warping method is used to calculate the similarity between the obtained prediction curve and the standard curve.

[0027] The present invention uses a triaxial inclination sensor, a triaxial acceleration sensor, and a soil humidity sensor to collect diversified data during the operation of the transmission line tower. In cooperation with the neural network algorithm model, it is beneficial to deeply mine the data and effectively improve the accuracy of predicting geological disasters. In addition, the acceleration signal obtained by the triaxial acceleration sensor is converted into a displacement signal by means of double integration, realizing the accurate monitoring of the minute displacement of the transmission line tower. The present invention realizes the real-time and accurate monitoring of the operation state of the transmission line tower using low-cost and low-power hardware, and accurately predicts possible geological disasters using the obtained data. Description of the Drawings

[0028] The attached drawings of the specification that form part of this application are used to provide a further understanding of the present invention. The schematic embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation to the present invention.

[0029] Figure 1 It is a schematic structural diagram of the geological disaster prediction device of the present invention;

[0030] Figure 2 It is a schematic flow diagram of the geological disaster prediction method of the present invention. Detailed Embodiments

[0031] In order to deepen the understanding of the present invention, the present invention will be further described in detail below in conjunction with embodiments and the attached drawings.

[0032] As Figure 1 shown, in this embodiment, the geological disaster prediction device for monitoring transmission line towers includes a power supply unit for supplying power to each unit and a user (centralized control) terminal.

[0033] A collection unit for collecting the tilt angle signal, acceleration signal of the transmission line tower to be monitored, and the soil humidity signal at the location where the transmission line tower to be monitored is located.

[0034] A wireless transceiver module for receiving the data collected by the collection unit.

[0035] A control unit for processing and analyzing the collected data received by the wireless transceiver module and obtaining geological disaster prediction data.

[0036] A storage module, the storage module is used to receive and store the collected data sent by the wireless transceiver module and the geological disaster prediction data obtained by the control unit.

[0037] A communication module; for sending the geological disaster prediction data obtained by the control unit to the user terminal.

[0038] The collection unit includes a three-axis inclinometer, a three-axis accelerometer, and a soil humidity sensor. The three-axis inclinometer and the three-axis accelerometer are placed at the top of the transmission line tower to be monitored, and the soil humidity sensor is placed below the ground surface at the location where the transmission line tower to be monitored is located.

[0039] The control unit, the wireless transceiver module, the storage module, and the communication module are placed in the middle and lower parts of the transmission line tower to be monitored.

[0040] The control unit includes a data preprocessing module, a neural network model, and a data analysis module. The neural network model includes an input layer, a hidden layer, and an output layer. The data preprocessing module preprocesses the collected data transmitted by the wireless transceiver module. The neural network model is used to obtain a prediction curve based on the preprocessed data and the historical data of the transmission line towers where geological disasters have occurred to obtain a standard curve. The data analysis module is used to compare the prediction curve with the standard curve obtained from the historical data to obtain geological disaster prediction data.

[0041] The triaxial acceleration sensor is an ADXL355 triaxial accelerometer.

[0042] The wireless transceiver module is an RF433 radio frequency small module.

[0043] The communication module is an ME3616 standard narrowband cellular networking communication module.

[0044] The power supply module includes a solar panel, a charge and discharge module, and a lithium battery. The lithium battery is a 19000 mAH / 3.7V lithium iron phosphate battery.

[0045] A method for predicting geological disasters using the geological disaster prediction device as described above, as Figure 2 shown, includes:

[0046] Using the acquisition unit to acquire the tilt angle signal, acceleration signal of the transmission line tower to be monitored, and the soil humidity signal at the location of the transmission line tower to be monitored;

[0047] Converting the acquired acceleration signal into a displacement signal;

[0048] Preprocessing the obtained tilt angle signal, displacement signal, and soil humidity signal;

[0049] Taking the preprocessed tilt angle, displacement, and soil humidity data as feature vectors and inputting them into the neural network model, and the output result is a prediction curve;

[0050] Obtaining the tilt angle, acceleration, and soil humidity data of the transmission line towers where geological disasters have occurred from the historical data of the transmission line tower detection to obtain a standard curve;

[0051] Calculating the similarity between the obtained prediction curve and the standard curve to obtain geological disaster prediction data. The greater the similarity, the greater the possibility of a geological disaster occurring;

[0052] Sending the obtained geological disaster prediction data to the user terminal.

[0053] In the acquisition unit, the triaxial inclination sensor acquires the inclination angle signal of the transmission line tower to be monitored, the triaxial acceleration sensor acquires the acceleration signal of the transmission line tower to be monitored, and the soil humidity sensor acquires the soil humidity signal at the location of the transmission line tower to be monitored.

[0054] Further, the process of converting the acceleration signal collected by the triaxial acceleration sensor into a displacement signal is as follows: the original acceleration signal is acquired at a high speed and Fourier-transformed to convert it into the frequency domain space. In the frequency domain, the signal is subjected to two integral operations, and then the integral result is converted into a time-domain displacement signal through an inverse Fourier transform.

[0055] Further, the number of hidden layers of the neural network is 15. The activation function of each node neuron in the neural network is calculated using the Sigmoid function and normalized to the range of -1 to 1. The weight correction of the neural network can adopt the gradient descent method or the conjugate gradient method. The weight correction formula is as follows:

[0056] W(k + 1) = W(k) + ΔW(k)

[0057] In the formula: W(k + 1) and W(k) are the connection weights of adjacent training numbers between nodes of each layer of the neural network, ΔW(k) is the correction value of the weights, and k is the number of training times.

[0058] Further, the dynamic time warping method is adopted to calculate the similarity between the obtained prediction curve and the standard curve.

[0059] The above are only the preferred embodiments of the present invention and are not used to limit the present invention. For those skilled in the art, the present invention can have various changes and modifications. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A geological disaster prediction device, comprising a power supply unit and a user terminal, characterized in that, It further includes: A collection unit for collecting the tilt angle signal, acceleration signal of the transmission line tower to be monitored, and the soil humidity signal at the location where the transmission line tower to be monitored is located; A wireless transceiver module for receiving the data collected by the collection unit; A control unit for processing and analyzing the collection data received by the wireless transceiver module and obtaining geological disaster prediction data; A storage module for receiving and storing the collection data sent by the wireless transceiver module and the geological disaster prediction data obtained by the control unit; A communication module; For sending the geological disaster prediction data obtained by the control unit to the user terminal.

2. The geological disaster prediction device according to claim 1, characterized in that, The collection unit includes a three-axis inclinometer, a three-axis accelerometer, and a soil humidity sensor. The three-axis inclinometer and the three-axis accelerometer are placed at the top of the transmission line tower to be monitored, and the soil humidity sensor is placed below the ground surface at the location where the transmission line tower to be monitored is located.

3. The geological disaster prediction device according to claim 1, characterized in that, The control unit, wireless transceiver module, storage module, and communication module are placed in the middle and lower parts of the transmission line tower to be monitored.

4. The geological disaster prediction device according to claim 1, characterized in that, The control unit includes a data preprocessing module, a neural network model, and a data analysis module. The data preprocessing module preprocesses the collection data transmitted by the wireless transceiver module. The neural network model is used to obtain a prediction curve based on the preprocessed data and the historical data of the transmission line towers where geological disasters have occurred to obtain a standard curve. The data analysis module is used to compare the prediction curve with the standard curve obtained using historical data to obtain geological disaster prediction data.

5. The geological disaster prediction method based on the monitoring of transmission line towers as claimed in claim 1, wherein The three-axis accelerometer is an ADXL355 three-axis accelerometer.

6. A method for predicting geological disasters using the geological disaster prediction device according to claim 1, characterized in that, It includes: Using the collection unit to collect the tilt angle signal, acceleration signal of the transmission line tower to be monitored, and the soil humidity signal at the location where the transmission line tower to be monitored is located; Converting the collected acceleration signal into a displacement signal; Preprocessing the obtained tilt angle, displacement, and soil humidity data; Using the preprocessed tilt angle, displacement, and soil humidity data as feature vectors to input into the neural network model to obtain a prediction curve; From the historical data of the transmission line tower detection, obtaining the tilt angle, acceleration, and soil humidity data of the transmission line towers where geological disasters have occurred to obtain a standard curve; Calculating the similarity between the obtained prediction curve and the standard curve to obtain geological disaster prediction data. The greater the similarity, the greater the possibility of a geological disaster occurring; Sending the obtained geological disaster prediction data to the user terminal.

7. The method for predicting geological disasters by the geological disaster prediction device according to claim 6, characterized in that, In the collection unit, the three-axis inclinometer collects the tilt angle signal of the transmission line tower to be monitored, the three-axis accelerometer collects the acceleration signal of the transmission line tower to be monitored, and the soil humidity sensor collects the soil humidity signal at the location where the transmission line tower to be monitored is located.

8. The geological disaster prediction method according to claim 6, characterized in that, The process of converting the acceleration signal collected by the three-axis accelerometer into a displacement signal is as follows: High-speed collect the original acceleration signal and perform Fourier transform to convert it into the frequency domain space. Perform two integral operations on the signal in the frequency domain, and then convert the integral result into a time-domain displacement signal through inverse Fourier transform.

9. The geological disaster prediction method according to claim 6, wherein, The number of hidden layers of the neural network is 15. The activation function of each node neuron in the neural network is calculated using the Sigmoid function and normalized to the range of -1 to 1. The weight correction of the neural network can adopt the gradient descent method or the conjugate gradient method, and the weight correction formula is as follows: W(k + 1) = W(k) + ΔW(k) Where: W(k + 1) and W(k) are the connection weights of adjacent training numbers between nodes of each layer of the neural network, ΔW(k) is the correction value of the weights, and k is the number of training times.

10. The geological disaster prediction method according to claim 6, wherein, The dynamic time warping method is used to calculate the similarity between the obtained prediction curve and the standard curve.

Images