Multi-Channel Time-Domain Boring-Vibration-Enhancement Method Using RNN Networks

SIMPLE SUMMARY: Tree trunk damage can be influenced by multiple factors, among which trunk-boring insect infestation plays a significant role. Early external detection of such damage poses challenges. Manual observation remains the prevailing method for controlling tree trunk pests, but it demands a substantial workforce and yields limited outcomes. To address these limitations, acoustic technology has gained popularity, using vibration probes embedded in tree trunks to capture vibrations produced by insect larvae feeding, thereby facilitating the detection of pest larvae. However, traditional methods primarily rely on single-channel vibration signal acquisition, often assuming the proximity of the vibration probe to the sound source. Nevertheless, when the probe’s position exceeds a certain distance from the original, capturing effective drilling vibration signals becomes difficult due to noise interference and other factors. To overcome this constraint, we have developed a novel multi-channel drilling vibration signal acquisition board that enables the distribution of multiple vibration probes at different locations on the tree trunk, allowing simultaneous collection of vibration signals from diverse probes. Additionally, we have devised a multi-channel signal separation model based on attention mechanisms, which effectively denoises and recovers clean target signals from noisy recordings. Experimental results demonstrate that this approach significantly enhances the detection efficiency of trunk-boring insects. ABSTRACT: The larvae of certain wood-boring beetles typically inhabit the interior of trees and feed on the wood, leaving almost no external traces during the early stages of infestation. Acoustic techniques are commonly employed to detect the vibrations produced by these larvae while they feed on wood, significantly increasing detection efficiency compared to traditional methods. However, this method’s accuracy is greatly affected by environmental noise interference. To address the impact of environmental noise, this paper introduces a signal separation system based on a multi-channel attention mechanism. The system utilizes multiple sensors to receive wood-boring vibration signals and employs the attention mechanism to adjust the weights of relevant channels. By utilizing beamforming techniques, the system successfully removes noise from the wood-boring vibration signals and separates the clean wood-boring vibration signals from the noisy ones. The data used in this study were collected from both field and laboratory environments, ensuring the authenticity of the dataset. Experimental results demonstrate that this system can efficiently separate the wood-boring vibration signals from the mixed noisy signals.