Bearings are very important components in mechanical equipment, and detecting bearing failures helps ensure healthy operation of mechanical equipment and can prevent catastrophic accidents. Most of the well-established detection methods do not take into account the correlation between signals and are difficult to accurately identify those fault samples that have a low degree of failure. To address this problem, we propose a graph neural network-based bearing fault detection (GNNBFD) method. The method first constructs a graph using the similarity between samples; secondly the constructed graph is fed into a graph neural network (GNN) for feature mapping, and the samples outputted by the GNN network fuse the feature information of their neighbors, which is beneficial to the downstream detection task; then the samples mapped by the GNN network are fed into base detector for fault detection; finally, the results determined by the integrated base detector algorithm are determined, and the topnsamples with the highest outlier scores are the faulty samples. The experimental results with five state-of-the-art algorithms on publicly available datasets show that the GNNBFD algorithm improves the AUC by 6.4% compared to the next best algorithm, proving that the GNNBFD algorithm is effective and feasible.

Wide-body dump trucks in open-pit mines frequently operate under high loads and severe road conditions, demanding superior dynamic performance from their suspension systems. Existing studies tend to focus only on the influence of individual parameters on the dynamic characteristics of hydro-pneumatic suspensions, lacking systematic analysis of parameter coupling effects and optimal parameter combinations. Taking the two-stage pressure hydro-pneumatic suspension of a wide-body dump truck as the research object, this paper theoretically analyzes its working characteristics and establishes an AMESim model under multiple excitation conditions to reveal how parameter interactions affect the dynamic performance of the suspension. With peak liquid pressure, maximum liquid pressure fluctuation, and maximum vehicle body vertical acceleration as optimization objectives, a multi-objective optimization algorithm is employed to determine the optimal suspension parameters. The results indicate that the interactive responses of damping orifice diameter and check valve diameter with respect to peak pressure and body vertical acceleration exhibit strong nonlinearity. Compared with the original parameter scheme, the optimized design reduces peak liquid pressure, maximum pressure fluctuation, and peak body vertical acceleration by 8.76%, 29.1%, and 11.7%, respectively, significantly improving vehicle ride comfort and mitigating pressure oscillations in the hydro-pneumatic suspension. The research results can provide theoretical support and engineering reference for intelligent operation and maintenance of mine heavy equipment, optimization design of suspension systems and efficient and reliable operation.