Zhang Xin

The Hong Kong University of Science and Technology | UST · Department of Mechanical Engineering

Massive number of applications involve data with underlying relationships embedded in non-Euclidean space. Graph neural networks (GNNs) are utilized to extract features by capturing the dependencies within graphs. Despite groundbreaking performances, we argue that Multi-layer perceptrons (MLPs) and fixed activation functions impede the feature extr...

The digital twin (DT) is recognized as a promising technology for achieving enhanced monitoring, control, and prediction of physical systems, contributing to increased reliability and effectiveness. While most researchers have concentrated on developing DTs for shop-floor and machine tools, there has been limited attention given to human operators....

Abnormal mechanical properties of Francis turbine units (FTUs) lead to unstable output power and operation fault, and may cause catastrophic hazards. At present, computational fluid dynamics (CFD) and machine learning (ML) methods are popular in predicting FTUs' mechanical behaviors, but there are limitations as follows: 1) CFD simulations focus on...

Recently, research on multisensor fault diagnosis under noisy signals has gained significant attention. Due to various degrees of external interference and differences in sensor precision, the signal quality across different channels is inconsistent. These discrepancies are often neglected by fault diagnosis models and are also difficult to capture...

Recently, rotating machinery fault diagnosis studies based on graph neural networks (GNN) have received some satisfactory achievements. But most of them are based on the analysis of the single sensor signals, which cannot capture the comprehensive fault information, especially aiming at large rotating machineries. A few research using GNN for multi...

Objective: To develop two intelligent diagnosis models of detrusor overactivity (DO) based on deep learning to assist doctors no longer heavily rely on visual observation of urodynamic study (UDS) curves. Methods: UDS curves of 92 patients were collected during 2019. We constructed two DO event recognition models based on convolutional neural ne...

Recently, the rapid development of digital twin (DT) technology has been regarded significant in Cyber-physical systems (CPS) promotion. Scholars are focusing on the theoretical architecture and implementing applications, in order to establish a high-fidelity, dynamic, and full-lifecycle DT model and achieve a deep fusion of real and virtual. As a...

Recently, graph data analysis receives attentions in mechanical fault diagnosis. Edge connection of the input graph indicates that neighbor nodes share the same fault type, but differences in importance between neighbor nodes is rarely demonstrated. Also, noise is unavoidable during signal acquisition, affecting the quality and reliability of const...

Recently, numerous new data-driven methods have been proposed. But most of them focused on the innovation of models and algorithms, and rarely discussed and optimized from the perspective of data and samples. However, the reliability of sample quality directly determines the effectiveness of machine learning models. In this paper, a novel data-driv...

Data augmentation technology has achieved great success to expand the training set for several years. As a representative technology, generative adversarial network and its variants are widely applied in many data augmentation tasks. But the quality of training samples is rarely considered. In this paper, a novel assessable data augmentation named...

Metamodels have been widely used as an alternative for expensive physical experiments or complex, time-consuming computational simulations to provide a fast but accurate analysis. However, challenge remains in the prior determination of the most suitable metamodel for a particular case because of the lack of information about the actual behavior of...

Deep learning has achieved much success in mechanical intelligent fault diagnosis in recent years. However, many deep learning methods cannot fully extract fault information to recognize mechanical health states when processing high-dimensional samples. Therefore, a multi-model ensemble deep learning method based on deep convolutional neural networ...

Aiming at solving the problem of insufficient labeled samples in mechanical equipment fault diagnosis, a semi-supervised fault recognition model based on Laplace Eigenmap (LE) and Deep Belief Network (DBN) is presented by combining the idea of manifold learning and deep learning. The model utilizes LE algorithm to directly extract the features from...

Aiming at making full use of the important messages contained in a small number of marked samples．The Laplacian Eigenmap ( LE) algorithm was improved by implementing confidence constraints on marked sample points．The semi-supervised fault diagnosis model based on the improved LE algorithm was presented． This model utilized the improved LE algorithm...