Research on load characteristics and fatigue damage of EMU motor bearing
December 2026
The durability of bearings has always been a key problem in engineering. In recent years, more and more research has focused on the service safety of bearings used in railway vehicles. In this paper,...
Foundation model-based federated learning for machine fault diagnosis
December 2026
Federated learning (FL) facilitates multiple enterprises to jointly train a powerful global model for machine fault diagnosis, while preserving the data privacy in each enterprise. However, data heterogeneity...
VLM-guided causal reasoning framework for cross-domain source-free industrial fault diagnosis
December 2026
Mechanical intelligent fault diagnosis (IFD) methods in cross-domain industrial environments are often constrained by data privacy regulations, distribution discrepancies between operating conditions,...
Optimization of knowledge graph search methods enabled by large language models with applications to fault diagnosis of electromechanical systems
December 2026
Under the trend of industrial intelligence upgrading, electromechanical systems serve as a crucial component for ensuring the normal operation of equipment. The accuracy of fault diagnosis directly...
Knowledge extraction and retrieval-augmented generation for intelligent maintenance of wind power equipment based on graph attention networks
December 2026
The adoption of deep learning in intelligent operation and maintenance of wind turbines has improved fault detection and classification accuracy. However, most existing studies focus primarily on the...
Fault inference diagnosis based on causal network and large language model-enhanced knowledge graph network
December 2026
Current research in mechanical fault inference diagnosis primarily relies on knowledge graph networks (KGN) for reasoning. Compared to traditional diagnostic methods, KGN offers advantages in knowledge...
An LLM-based framework for state of health estimation of lithium-ion batteries
December 2026
Accurate state of health (SOH) estimation is essential for ensuring the reliability and safety of lithium-ion batteries. However, existing methods often suffer from complex modeling requirements and...
Exploring prior-structured low-rank adaptation for predictive maintenance based on time series foundation model
December 2026
Predictive maintenance for industrial equipment is hampered by nonstationary dynamics and the scarcity of labeled data. In contrast, large foundation models offer the potential for universal sequence...
Large models for machinery fault diagnosis: Current advances and future directions
December 2026
Machinery fault diagnosis (MFD) is critical for the intelligent operation and maintenance of advanced equipment, contributing to enhanced safety, improved efficiency and reduced operating costs. Early...
Vector mirroring algorithm: A metaheuristic method for efficient optimization
December 2026
Metaheuristic methods are effective in solving complex optimization problems but often require sophisticated iterative strategies that lead to high computational costs, especially in high-dimensional...
Modality alignment-driven large language model for wind farm power forecasting
December 2026
Accurate forecasting of wind farm power output plays a vital role in grid dispatching, optimizing transactions in electricity markets, and enhancing the overall operational security of power systems....
In-plane modal characteristics of tire: An improved flexible ring model with damping and contact effects
December 2026
As tire is the only part of contact between a vehicle and the road, the dynamic response property of a tire under different loads is of great importance to fully understand the tire performance. Simplifying...
The role of transversal ultrasonic vibration and tool geometry on surface integrity and fatigue performance in drilling of Al-Li alloy
December 2026
Advanced hole-making technology is crucial and important in the aviation industry. In this study, we proposed a new drilling method that combines transversal ultrasonic vibration with tool blunt geometry,...
Study on the adaptability of elliptic continuous high-speed ultrasonic vibration cutting for complex rotating parts made of FGH96
Available online 9 June 2026
Continuous cutting cannot open the cutting area; therefore, cutting fluid cannot enter the region for cooling and lubrication. The resulting high cutting temperature and force reduce cutting speed,...
Dynamics modeling of gear honing machine based on parameter identification
Available online 5 June 2026
Gear honing is an important gear finishing process that can effectively improve tooth surface texture and reduce transmission noise. However, in the actual gear honing process, chatter often occurs,...
Physics-Data-Driven Hybrid State Estimation for Articulated Heavy Vehicles in Vehicle-Road-Cloud Cooperative Framework
Available online 3 June 2026
Owing to their multi-body configuration, the handling and stability of articulated heavy vehicles have received increasing attention in recent years. Accurate estimation of the trailer states and the...
FM-LLM: A Lightweight Multimodal LLM with Simulation-Augmented Data for Mechanical Fault Diagnosis
Available online 2 June 2026
Industrial fault diagnosis is a key component of intelligent manufacturing systems. Diagnostic accuracy directly influences the safety of production systems and the efficiency of equipment operation...
Case-Driven Fault Diagnosis with Advanced Hallucination Mitigation in Large Language Models: A Way Towards Practical Applications
Available online 2 June 2026
The integration of large model paradigms into industrial PHM fault diagnosis offers new potential for multi-source knowledge fusion and complex reasoning. However, hallucinations, including logical...
An analytical model for the capacitance of stainless steel braided reinforced Teflon aviation hoses
Available online 26 May 2026
Stainless Steel Braided Reinforced Teflon Hose (SSBRTH), as an extensively used component in the aviation hydraulic system, has a huge impact on system performance. Because of its elasticity, the calculation...
A novel Jacobian method for kinematically redundant parallel mechanisms with configurable platforms
Available online 24 May 2026
Kinematic redundancy emerges as a prominent subject in the research of parallel mechanisms on account of the exceptional flexibility and substantial workspace it provides. However, for kinematically...
Enhanced tribological performance of laser-cladded In718 coatings: Cladding parameters optimization via thermo-mechanical simulation
Available online 22 May 2026
Cladding high-hardness In718 alloy onto ductile iron emerges as an effective solution to mitigate interfacial degradation, owing to the alloy’s superior resistance to corrosion, oxidation, wear and...
Ex-SPGCAN: Signal-Prior-Guided Channel Attention for Explainable Fault Diagnosis of Diesel Engine Under Variable Operating Conditions
Available online 20 May 2026
Diesel engine vibration signals contain multiple physically meaningful impact components that exhibit significant shifts in their distributions under variable operating conditions, posing substantial...
Mechanism of Rotary Ultrasonic Elliptical Milling (RUEM) of GH2132 and Study on Its Surface Integrity: Taking Efficiency Improvement in Stator Blade Machining as an Example
Available online 20 May 2026
GH2132 superalloy is specifically used in the manufacture of aero-engine stator blades. However, its superior performance leads to challenges such as poor machinability and difficult control of surface...
TimeGPT for Mechanical System Degradation Assessment: A Large Time Series Model Approach
Available online 19 May 2026
Accurate degradation assessment of mechanical systems is critical for ensuring reliability, safety, and cost efficiency in modern industrial operations. Conventional data-driven methods, including classical...
Self-Supervised Sequence Learning Framework for Monocular Visual Odometry with Spatio-Temporal Correlation
Available online 11 May 2026
Visual odometry (VO) estimates the ego-motion of moving objects from consecutive image sequences captured by single or multiple on-board cameras. Most existing VO methods only estimate the pose from...
