Tower bolt state monitoring method and device based on stack type support vector machine

Abstract

The invention discloses a tower bolt state monitoring method and device based on a stack type support vector machine. The tower bolt state monitoring method comprises the steps: collecting and preprocessing a vibration data set; carrying out wavelet transformation on the preprocessed data to construct a feature vector; training an adversarial support vector machine A-SVM by using the feature vector; training a stack type support vector machine S-SVM; and utilizing the trained stack type support vector machine model to realize automatic monitoring of the tower state. The tower bolt state monitoring device is characterized in that the input end of an AD acquisition module is connected with a vibration speed sensor; the output end of the AD acquisition module is connected with an FPGA; the FPGA is connected with a GPRS module and an up2 development board; the up2 development board sends a control instruction to a control relay module, and the output end of the control relay module is connected with the vibration speed sensor; and the GPRS module communicates with a far-end upper computer. According to the tower bolt state monitoring method and device, the safety state of the tower canbe monitored, and accidents caused by bolt loosening of the tower are reduced, and safe and stable operation of the power tower and a power transmission line is guaranteed.

Description

technical field [0001] The invention relates to a bolt state monitoring technology in the field of signal processing and fault diagnosis, in particular to a tower bolt state monitoring method and device based on a stacked support vector machine. Background technique [0002] With the continuous improvement of the electrification level in our country, the power transmission capacity and transmission lines continue to grow. As an important part of transmission lines, the safe and reliable operation of power towers is related to the safety of the entire power grid. Due to the large number and wide distribution of power towers, there are many difficulties in the daily maintenance and repair of power towers in the power sector. At the same time, due to the influence of environmental factors, human factors, etc., the bolts of the power tower may loosen or even fall off, which will not only bring safety hazards to the tower and transmission lines, but also cause serious safety pro...

AI Technical Summary

Problems solved by technology

At the same time, due to the influence of environmental factors, human factors, etc., the bolts of the power tower may loosen or even fall off, which will not only bring safety hazards to the tower and transmission lines, but also cause serious safety problems to the surrounding pedestrians and people. property loss

The traditional maintenance method of regularly sending personnel to the site not only has a long cycle, but also has a heavy workload and high labor costs, which is not conducive to the safe and economical operation of power companies

At present, the main way to detect the loose bolts of power towers is still manual inspection. The on-site personnel hit the tower with a hammer and judge whether there are loose bolts in the tower by listening to the echo. It relies heavily on personal experience on site, and the judgment is highly subjective and accurate. low rate

Images