Automated Health Condition Diagnosis of in situ Wood Utility Poles Using an Intelligent Non-Destructive Evaluation (NDE) Framework

Abstract

Wood utility poles are widely applied in power transmission and telecommunication systems in Australia. Because of a variety of external influence factors, such as fungi, termite and environmental conditions, failure of poles due to the wood degradation with time is of common occurrence with high degree uncertainty. The pole failure may result in serious consequences including both economic and public safety. Therefore, accurately and timely identifying the health condition of the utility poles is of great significance for economic and safe operation of electricity and communication networks. In this paper, a novel non-destructive evaluation (NDE) framework with advanced signal processing and artificial intelligence (AI) techniques is developed to diagnose the condition of utility pole in field. To begin with, the guided waves (GWs) generated within the pole is measured using multi-sensing technique, avoiding difficult interpretation of various wave modes which cannot be detected by only one sensor. Then, empirical mode decomposition (EMD) and principal component analysis (PCA) are employed to extract and select damage-sensitive features from the captured GW signals. Additionally, the up-to-date machine learning (ML) techniques are adopted to diagnose the health condition of the pole based on selected signal patterns. Eventually, the performance of the developed NDE framework is evaluated using the field testing data from 15 new and 24 decommissioned utility poles at the pole yard in Sydney.

Combined machine learning–wave propagation approach for monitoring timber mechanical properties under UV aging

“…Utilizing ML for developing datadriven models has been practiced for properties prediction, 22,53 damage and fault detection, 37 and health monitoring of materials and structures. 44,45,54,55 It accounts for materials and process high variability and facilitates developing intelligent in-situ monitoring models. In this study, decision tree regression modeling was performed for timber properties prediction.…”

“…Defect detection is of great importance for condition monitoring and damage analysis in timber utility poles. [44][45][46] Further investigation can be performed to assess the impact of natural defects on the UV degradation of timber and the performance of the Lamb wave propagation method for monitoring the mechanical properties of defected wood under UV aging. In this study, the wave propagation tests were performed in the longitudinal-tangential plane of the wood specimens resulting in predicting the mechanical properties of wood in the longitudinal direction.…”

“…In this case, feature extraction from the frequency and time-frequency domains may be practiced using the empirical mode decomposition and wavelet transform techniques. 45,46 Having a higher number of extracted features and a more complex dataset, the decision tree modeling can be modified and replaced by the random forest analysis, which combines the output of multiple decision trees using a voting scheme 65 to generate the final output. The performance of the decision tree with random forest modeling and ANNs may be compared in future studies, if the ability to interpret the model outcome can be compromised.…”

“…The guided wave propagation method has been also successfully employed for health monitoring of wood utility poles. [44][45][46] Despite the effectiveness of the Lamb wave method for material characterization and damage detection, studies on employing the Lamb waves for the characterization of the mechanical properties of wood materials under UV conditions are limited. Specifically, it is not studied whether the Lamb wave characteristics can be accurately linked to the photodegradation of wood materials exposed to UV radiation.…”

A Hybrid Data-Fusion System by Integrating CFD and PNN for Structural Damage Identification

“…Structural damage identification is an essential approach to prevent a sudden collapse of structures and avoid casualties and heavy economic losses [1][2][3]. A series of damage detection methods have been proposed [4][5][6][7][8], and health monitoring systems have been developed and installed in a number of large-scale engineering structures.…”