Sensor drift is one of the severe issues that gas sensors suffer from. To alleviate the sensor drift problem, a gas sensor drift compensation approach is proposed based on local discriminant subspace projection (LDSP). The proposed approach aims to find a subspace to reduce the distribution difference between two domains, i.e., the source and target domain. Similar to domain regularized component analysis (DRCA) which is a recently proposed sensor drift correction method, the mean distribution discrepancy is minimized in the common subspace in our approach. LDSP extends DRCA in two aspects, i.e., it not only takes the label information of the source data into consideration to reduce the possibility of the case that samples in the subspace with different class labels stay close to each other, but also borrows the idea of locality-preserving projection to deal with multimodal data. Specifically, inspired by local Fisher discriminant analysis (LFDA), the label information is utilized to maximize the local between-class variance of source data in the latent common subspace and simultaneously minimize the local within-class variance. The formulation of LDSP is a generalized eigenvalue problem that can be readily solved. The experimental results have shown the proposed method outperforms other gas sensor drift compensation methods in terms of classification accuracy on two public gas sensor drift datasets.

The conventional machine learning algorithm for analyzing ultrasonic signals to detect structural defects necessarily identifies and extracts either time- or frequency-domain features manually, which has problems in reliability and effectiveness. This work proposes a novel approach by combining convolutional neural networks (CNNs) and wavelet transform to analyze the laser-generated ultrasonic signals for detecting the width of subsurface defects accurately. The novelty of this work is to convert the laser ultrasonic signals into the scalograms (images) via wavelet transform, which are subsequently utilized as the image input for the pretrained CNN to extract the defect features automatically to quantify the width of defects, avoiding the necessity and inaccuracy induced by artificial feature selection. The experimentally validated numerical model that simulates the interaction of laser-generated ultrasonic waves with subsurface defects is first established, which is further utilized to generate adequate laser ultrasonic signals for training the CNN model. A total number of 3104 data are obtained from simulation and experiments, with 2480 simulated signals for training the CNN model and the remaining 620 simulated data together with 4 experimental signals for verifying the performance of the proposed algorithm. This approach achieves the prediction accuracy of 98.5% on validation set, particularly with the prediction accuracy of 100% for the four experimental data. This work proves the feasibility and reliability of the proposed method for quantifying the width of subsurface defects and can be further expanded as a universal approach to various other defects detection, such as defect locations and shapes.

Structural health monitoring (SHM) has been increasingly investigated for decades. Different physical principles have been developed for damage identification, such as electronics, mechanics, magnetics, etc., with different coverage (i.e., global, large‐area, and local monitoring) and sensitivity. Mechanical acousto‐ultrasonic‐based methods have formed a big family in SHM technologies. Multiple wave/resonance modes have been utilized for versatile SHM tasks. The permanently integrated sensing networks play a significant role in achieving a cost‐effective and reliable SHM system, with major concerns including weight increase for large‐scale deployment and conformity for complex geometry structures. In this review, typical acousto‐ultrasonic sensors made of different material systems are discussed, along with advantages and limitations. Moreover, advanced network installation methods have been introduced, including surface‐mounting with pre‐integrated networks on substrates and in situ printing, and embedding with composite layup and metal additive manufacturing. Sensor versatility and usage in multi‐scale SHM techniques are then highlighted. Different wave/resonance modes are transmitted and received with corresponding elements and network designs. In conclusion, this systematic review mainly covers a collection of acousto‐ultrasonic sensors, two modalities of network installation, and their employment with various SHM methods, hopefully providing a useful guide to building lightweight and conformal networks with passive or active‐passive sensors, and developing complete and reliable SHM strategies by integrating different damage identification methods on multiple scales.

In marine environments, microbial attacks on metallic materials result in microbiologically influenced corrosion (MIC), which could cause severe safety accidents and high economic losses. To date, MIC of a number of metallic materials ranging from common steels to corrosion-resistant ferrous alloys has been reported. The MIC process has been explained based on (1) bio-catalyzed oxygen reduction; (2) kinetics alternation of the corrosion process by increasing the mass transport of the reactants and products; (3) production of corrosive substances; and (4) generation of auxiliary cathodic reactants. However, it is difficult to have a clear understanding of the MIC mechanism of ferrous alloys due to the interdisciplinary nature of MIC and lack of deep knowledge about the interfacial reaction between the biofilm and ferrous alloys. In order to better understand the effect of the MIC process on ferrous alloys, here we comprehensively summarized the process of biofilm formation and MIC mechanisms of ferrous alloys.

Tactile sensing with spiking neural networks (SNNs) has attracted increasing attention in the past decades. In this article, a novel SNN framework is proposed for the tactile surface roughness categorization task. In contrast to supervised SNN methods such as ReSuMe and Tempotron that require prespecifying target spike trains, the presented method performs the classification through directly comparing the distance between multineuron spike trains. Unlike simple spike train fusion methods using average pairwise spike train distance or pooled spike train distance, the proposed method merges spike trains from different neurons with the multineuron spike train distance, which can capture the complex correlation of multiple spike trains. Specifically, the spike trains are generated via the Izhikevich neurons from tactile signals. The similarity of the multineuron spike trains is computed using the multineuron Victor-Purpura spike train distance, which can be efficiently implemented in an inductive manner. The classification can be performed by incorporating k-nearest neighbors and the multineuron spike train distance as a similarity metric. The proposed framework is quite general, i.e., other multineuron spike train distances and spike train kernel-based methods can be readily incorporated. The effectiveness of the proposed method has been demonstrated on a tactile data set by comparing it with various feature- and spike-based methods.