The elevator door system plays a crucial role in ensuring elevator safety. Fault prediction is an invaluable tool for accident prevention. By analyzing the sound signals generated during operation, such as component wear and tear, the fault of the system can be accurately determined. This study proposes a GNN-LSTM-BDANN deep learning model to account for variations in elevator operating environments and sound signal acquisition methods. The proposed model utilizes the historical sound data from other elevators to predict the remaining useful life (RUL) of the target elevator door system. Firstly, the opening and closing sounds of other elevators is collected, followed by the extraction of relevant sound signal characteristics including A-weighted sound pressure level, loudness, sharpness, and roughness. These features are then transformed into graph data with geometric structure representation. Subsequently, the Graph Neural Networks (GNN) and long short-term memory networks (LSTM) are employed to extract deeper features from the data. Finally, transfer learning based on the improved Bhattacharyya Distance domain adversarial neural network (BDANN) is utilized to transfer knowledge learned from historical sound data of other elevators to predict RUL for the target elevator door system effectively. Experimental results demonstrate that the proposed method can successfully predict potential failure timeframes for different elevator door systems.

As a key component for transmitting electrical signals, the electrical contact performance of electrical connectors is directly affected by the closing amount of the socket. It is urgent to explore the relationship between contact resistance and the closing amount of cylindrical groove electric connectors, as well as the range of the closing amount when their comprehensive performance is optimal in vibration environments. Based on Hertz contact theory, the long- and short-axis parameters of the contact elliptical surface were obtained using the Boussinesq solution and the contact deformation coordination equation. An electrical contact resistance (ECR) theoretical model was obtained using Holm’s electric contact theory and the GW contact model. According to the ECR and long- and short-axis parameters of the contact elliptical surface and the theoretical model of contact resistance, an ECR model based on changes in the initial closing amount (deflection) of the socket spring was established by introducing the cantilever beam model of the socket spring. Then, the failure mechanism of fretting wear and the change mechanism of the ECR of the electrical connectors under a vibration environment were analyzed using the sinusoidal vibration test of electric connectors. The optimal range of the initial closing amount of the cylindrical-groove-closing-type electrical connector socket spring was determined, providing a reference for the reliability designs of electrical connectors.

In order to get a rapid assessment on the storage reliability of high-reliable and long-life products within the storage period, accelerated degradation test data with a large amount of reliability information of product is adopted. Conducting a constant-stress accelerated degradation test(CSADT) is generally very costly as it requires a large sample size and long time for test. To overcome this problem, it is necessary to carry out research on modeling and statistical analysis methods of step-stress accelerated degradation test (SSADT). Taking electrical connectors as the object, a research is conducted on statistical model and assessment method for SSADT. On the basis of mixed-effect degradation path model, the statistical model of SSADT for electrical connectors is presented, the maximum likelihood method for SSADT data based on mixed-effect degradation model is proposed. SSADT accelerated by temperature stress is conducted to Y11X-1419 type of electrical connectors, and the storage reliability is assessed with the SSADT data. Compared with the result obtained from accelerated life test, the reliability estimation of 32-year storage period for electrical connectors obtained from SSADT data only have a difference of 0.869%, which validates the accuracy of the degradation model and the feasibility of the test data statistic analysis method put forward.

Studies on maintenance and inventory optimization have been frequently combined to cut the total operation and maintenance costs of multicomponent systems. Most existing studies assume that components are stochastically independent and only collaborate on inventory management-related resources. In practice, stochastic dependencies exist in most complex systems, and limited maintenance time becomes a crucial resource shared by all components during multimission selective maintenance (SM). Neglecting these features reduces the practicality of policies. To address this limitation, we investigate joint multimission SM and inventory optimization for systems considering stochastic dependency among components. First, an extended factor analysis model incorporating the effects of working conditions is proposed, based on which diverse and dependent degradation processes of components under multiple missions can be well characterized. Then, the sequential optimization of joint multimission SM and inventory policies, which consider information about component degradation states, available resources, and mission profiles simultaneously, is developed using a continuous-state Markov decision process. Decision variables are optimized by an efficient reinforcement learning algorithm. Conclusively, the superiority of the proposed method is illustrated using a numerical example of a photovoltaic system.

According to the change characteristics in the toughness of the metal material during the fatigue damage process, the fatigue tests were carried out with the standard 18CrNiMo7-6 material. Scanning the fracture with an electron microscope explains the lack of linear cumulative damage in the mechanism. According to the obtained results, a nonlinear damage accumulation model which considered the loading sequence state under the toughness dissipation model was established. The recursive formula was devised under two-level. The fatigue test data verification of three metal materials showed that using this model to predict fatigue life is satisfactory and suitable for engineering applications.