Abstract
This paper presents the development of a methodology to detect and evaluate faults in cable-stayed towers, which are part of the infrastructure of Brazil’s interconnected electrical system. The proposed method increases system reliability and minimizes the risk of service failure and tower collapse through the introduction of predictive maintenance methods based on artificial intelligence, which will ultimately benefit the end consumer. The proposed signal processing and interpretation methods are based on a machine learning approach, where the tower vibration is acquired from accelerometers that measure the dynamic response caused by the effects of the environment on the towers through wind and weather conditions. Data-based models were developed to obtain a representation of health degradation, which is primarily based on the finite element model of the tower, subjected to wind excitation. This representation is also based on measurements using a mockup tower with different types of provoked degradation that was subjected to ambient changes in the laboratory. The sensor signals are preprocessed and submitted to an autoencoder neural network to minimize the dimensionality of the resources involved, being analyzed by a classifier, based on a Softmax configuration. The results of the proposed configuration indicate the possibility of early failure detection and evolution evaluation, providing an effective failure detection and monitoring system.
Highlights
In recent years, the growing demand for electricity and the wealth of water resources in the Brazilian territory have led to an increased adoption of guyed towers for the distribution network due to their lower cost
We proposed a noninvasive approach for anomaly detection and severity estimation for monitoring cable-stayed power transmission towers
The performance of two proposed neural network configurations was analyzed for two datasets, where the first was based on a finite element method of a real tower and the second was based an experimental one with data acquired from a mockup laboratory tower
Summary
The growing demand for electricity and the wealth of water resources in the Brazilian territory have led to an increased adoption of guyed towers for the distribution network due to their lower cost. The overall expected result is an improvement in maintenance costs, a significant reduction in field inspections and an increase in the reliability of the system and the quality of service Given this problem, many studies have been aimed at assessing the structural condition of guyed towes. This paper proposes a methodology to detect incipient failures and assess their severity in order to avoid the occurrence of a structural collapse For this dual purpose, data-driven models of normal behavior were created and trained using two autoencoder and classifier neural network configurations, based on simulated and experimental datasets. Data-driven models of normal behavior were created and trained using two autoencoder and classifier neural network configurations, based on simulated and experimental datasets These models were used to detect anomalies through comparative analysis of a testing subset of signals from the datasets. Training data are presented repeatedly and net weights are adjusted by backpropagation until the desired input–output mapping error falls below a small specified threshold
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
