Transverse vibration measurement of beam structures based on computer vision has been widely used, but most visual measurement methods require the installation of artificial markers at the measured positions. This makes the measurement of vibrations in some key position of beam structures difficult due to their inaccessibility. Therefore, the development of target-less approaches is important for some engineering applications. In this paper, a method for measuring displacement and vibration of beam structures visually is presented based on sub-pixel edge point tracking. Combining the principle of coordinate space transformation and the two-dimensional normal distribution characteristics of false edge parameters, false edges are eliminated to determine the position of structural edges accurately. This allows measurement of beam deflection and point tracking of the beam structure’s vibration. The effectiveness of the proposed method is verified through a cantilever beam vibration experiment and the measured data are compared using a traditional piezoelectric sensor (eddy current displacement sensor and accelerometer) and digital image correlation method. Compared with the traditional piezoelectric sensor methods, the maximum difference of the measured displacement was less than 2.4%. Compared with the digital image correlation method, the time series correlation of the proposed method with the reference measurements was 0.35% higher, and the main vibration frequency error was 0. The experiment proves that the proposed method can be used as an effective visual measurement method for target-less tracking of the transverse vibration of beam structures.

With the acceleration of urbanization process, the number of elevators in China has surged. Concurrently, the prevalence of older elevators has increased, leading to a rise in frequent malfunctions. In recent years, there has been a troubling frequency of elevator accidents resulting in casualties, which has had a negative social impact. The elevator braking system is crucial for ensuring the safe operation of the elevator, and brake failure is a significant contributor to elevator accidents. The failure modes of elevator brakes are complex and diverse, and the failure risk factors are mixed, correlated and unknown. Therefore, this paper is based on the Failure Mode and Effects Analysis (FMEA), focusing on the structural characteristics of the elevator brake to determine the equipment failure risk factors. Based on the accident prevention theory model (24Model) for comprehensive analysis of internal and external causes, this study identifies the comprehensive failure risk factors for elevator brakes. The study employs affiliation function to build the failure risk factor indicator system, the use of the Decision-making Trial and Evaluation Laboratory (DEMATEL) and Interpretative Structural Modeling (ISM) methods to analyze the hierarchical structure and internal relationship between the factors. Based on the research results, the factors contributing to the failure of elevator drum brakes can be identified and the interrelationships among these factors can be systematically elucidated. This analysis can serve as a valuable tool in pinpointing critical areas for routine elevator maintenance and upkeep, with the aim of minimizing the likelihood of drum brake malfunctions. Furthermore, the insights gained can inform the design and implementation of elevator monitoring and management systems, enabling a clearer focus on pertinent factors. Ultimately, this study furnishes a theoretical framework for the prevention and mitigation of such accidents.

With the rapid development of science and technology, the integration and complexity of aerospace vehicles, weaponry, and large-scale chemical equipment are becoming higher and higher. PHM plays an important role in realizing reductions in equipment loss due to failures in many fields. In order to systematically sort through the research history of PHM and deeply analyze the development status of AR and DT technologies in the field of PHM, to clarify the current technical challenges and future development directions and to provide valuable references and insights for researchers, engineers, and decision-makers in the related fields, this paper summarizes the development of PHM in the engineering field. This paper summarizes the development of PHM in the field of engineering, from the initial PHM used in aerospace to the current PHM systems supported by various advanced technologies; analyzes the advantages and shortcomings of the digital twin and augmented reality technologies used for PHM; and organizes and summarizes the future directions and future research focuses of PHM research based on the existing technologies (mainly digital twins and augmented reality). After systematic research and study, we found that the integration of augmented reality and digital twin technologies will provide superb simulation capabilities and immersive operation and bring new challenges and opportunities. Therefore, it is also imperative to address the challenges and limitations that hinder the seamless integration of the new technologies.

Elevator door systems are critical and failure-prone subsystems in elevators, with vibration signals characterized by strong nonlinearity, non-stationarity, and complex temporal dependencies under varying operating conditions. Existing fault diagnosis methods often struggle to effectively model these characteristics, particularly in capturing cross-scale dependencies between local transient disturbances and global temporal evolution patterns. To address this issue, a cross-scale spatiotemporal feature learning framework integrating adaptive time-frequency decomposition and deep feature fusion is proposed. Variational mode decomposition (VMD) is applied to decompose nonlinear vibration signals into intrinsic mode functions, while fast Fourier transform (FFT) is used to extract global spectral information, forming a multi-channel time-frequency representation. The convolutional neural network (CNN) module is designed to extract local transient features associated with mechanical impacts, while the bidirectional long short-term memory (BiLSTM) module models long-term temporal dependencies. Furthermore, a cross-attention mechanism is introduced to dynamically fuse local and global representations, enhancing discriminative feature learning under complex operating conditions. Experimental results on a representative elevator door fault dataset show that the proposed approach attained an average accuracy of 99.18% and an average F1-score of 99.13%. Compared with conventional machine learning and neural network-based methods, the proposed framework demonstrates superior diagnostic accuracy and robust performance under the evaluated experimental conditions. The findings indicate that the proposed approach serves as an efficient strategy for cross-scale spatiotemporal modeling of nonlinear and non-stationary vibration signals, with considerable promise for intelligent health monitoring and prognostic maintenance of elevator door systems.