Terahertz (THz) technology has firmly established itself as an effective sensing and nondestructive testing technique for the detection of substances and physico-chemical evaluation of materials and structural systems since its first emergence almost three decades ago. To date, both the effectiveness and accuracy of this technology have been extensively demonstrated in a myriad of applications across the spectrum of research and development all the way to process analytical technology, quality control, nondestructive testing, and structural health monitoring. These applications are generally enabled by the production and availability of advanced, versatile, robust, highly accurate, and industrially rugged THz spectroscopy and imaging systems, the unique properties of THz waves compared with other electromagnetic waves, as well as the advancements in electronics, photonics, and THz metamaterial systems development. This article presents a comprehensive state-of-the-art and state-of-the-practice review of sensing and nondestructive testing applications of THz technology and analyzes the role of THz metamaterials in enhancing the resolution and sensitivity of THz systems. The study also provides a general overview of the fundamentals of THz spectroscopy and imaging systems and discusses the suitability of THz sensing and nondestructive testing in a variety of real-world application scenarios ( e.g . composites’ defect detection and evaluation, paints and coatings thickness measurement and characterization, biomolecule detection, etc .). Aspects such as the noise caused by the presence of barriers, challenges with experimental implementations and operability of THz systems, long times required to acquire THz images, as well as limited customizability and portability of currently available THz systems are also discussed.

With the continuous development of computer technology, deep learning has been widely used in fault diagnosis and achieved remarkable results. However, in actual production, the problem of insufficient fault samples and the difference in data domains caused by different working conditions seriously limit the improvement of model diagnosis ability. In recent years, meta-learning has attracted widespread attention from scholars as one of the main methods of few-shot learning. It can quickly adapt to new tasks by training on a small number of samples. A fine-tuning prototypical network is proposed on meta-learning methods to address the challenges of fault diagnosis under few-shot and cross-domain. Firstly, the shuffle attention is used to enhance the feature extraction ability of the network and suppress irrelevant features. Then, the support set of the target domain is split into two parts: pseudo support set and pseudo query set, which are used to fine-tune the prototypical network and improve the model generalization. Finally, experiments are conducted on three rotating equipment datasets to verify the method’s effectiveness.

In recent years, with the in-depth development of intelligent technology, the application of deep learning combined with domain adaptive methods in mechanical cross-domain fault diagnosis has increased. However, in the actual environment, the state categories of the target domain that need to be tested may only constitute a subset of the source domain. A partial fault diagnosis method for rolling bearings is proposed to aim at the partial domain adaptive problem in mechanical fault classification. The method introduces the temperature decay strategy into the traditional softmax function, sharpens the weight distribution difference between the shared and outlier classes, uses the obtained class-level weights to weigh the source samples, and combines with the confrontation strategy to achieve domain adaption. In addition, a correction function is added to the fault classifier to improve the classification accuracy of the source domain samples. Three different bearing datasets were used to verify the effect of the proposed method. Finally, the interpretability of the proposed model is analyzed and explained by explainable artificial intelligence (XAI) technology.