Search

Detecting faults on the anchor rods of power transmission line towers is an essential procedure for guaranteeing the safety, operability, and availability of the electric power system. Such a measure aims to minimize the risk of tower collapse and the associated costs due to the lack of energy, injuries to people, and damage to the reputation of the companies involved. In this letter, we report an alternative noninvasive and nondestructive detection technique through the acquisition of electromagnetic scattering parameters. A novel machine learning (ML) approach is proposed in order to achieve the advantages of such a technique and to deal with the respective drawbacks due to the complexity of signals acquired. A strategy to artificially increase the number of relevant samples in the dataset through the simulations of computational models is performed. Different ML classification algorithms are compared in the task of detecting structural faults in anchor rods in order to define the most suitable to this application. Finally, experimental results show that the methodology proposed achieves a high detection accuracy, surpassing other known methods.

This paper introduces a new strategy to determine the soil permittivity and its loss tangent which uses simulation and measurement result for comparison. The setup of the measurement system includes a high frequency connector and a two-rod transmission line (TRTL) where one of the rods is embedded in an unknown-permittivity soil. In order to validate the simulation model by optimizing the complex permittivity of the soil from the measurement result a smart searching tool performed by the PSO (Particle Swarm Optimization) algorithm is applied. The measurements were carried out by a VNA (Vector Network Analyzer) to obtain the reflected signals from the TRTL for a non-parameterized soil. The effectiveness of the PSO algorithm is demonstrated by equalizing both simulated and measurement results of the soil complex permittivity in the simulation model.

Network parameters are capable of conveying information about the constitution of a medium in which a highfrequency wave propagates. In this paper, this characteristic is exploited in order to design a nondestructive system to detect corrosion in anchor rods of guyed towers. A compound database is built with the simulated and measured parameters return loss, input impedance, and voltage standing wave ratio for normal and faulty rods examples. Artificial neural networks are used to capture underlying characteristics of data and establish relationships between these parameters and the presence of corrosion in the rods, without the need for physical models. Experimental results show that the innovative use of a multiparameter strategy achieves a high accuracy and enhances the detection capacity of the system.

This paper presents a new methodology based on a FDR technique and machine learning structure to detect faults on anchor rods used in guyed towers of power transmission lines. Such faults are due to material loss in the rods, which it may break them, and may case the tower falling. The methodology is a non-destructive technique (NDT) that is based on frequency domain reflectometry (FDR). For detection, high frequency pulses are inserted into anchor rod samples and the reflection coefficient is analyzed and compared to that obtained in the simulation results. Samples of anchor rods with and without faults were simulated, fabricated, measured and classified by a machine learning structure to determine the presence or absence of the faults.

This paper presents a field application system for detecting structural faults on anchor rods of cable-stayed towers of power transmission lines, based on a nondestructive technique using frequency domain reflectometry analysis. A specific high frequency connector was designed to interface a portable vector network analyzer and the buried rods in the test field. The soil electric permittivity was modeled using a full-wave electromagnetic simulation software and measurements. A machine learning structure was developed for the measured S11-parameter signals from the distinct buried rods to binary classify them as normal or faulty. An accuracy greater than 98% was achieved by characterizing the system as reliable and feasible for a novel predictive maintenance process for ground-anchored metallic rods.