Bearings are critical yet vulnerable components in mechanical equipment, with potential failures that can significantly impact system performance. As stochastic resonance methods effectively convert noise energy into fault characteristic energy within bearing vibration signals, they remain a research focus in bearing fault diagnosis. This study proposes a coupled neuron model based on biological stochastic resonance effects for processing bearing vibration signals. To enhance parameter optimization, we develop an improved deep reinforcement learning algorithm that incorporates a prioritized experience replay buffer into the network architecture. Using the SNR as the evaluation metric, the algorithm performs data screening on the replay buffer parameters before training the deep network for predicting coupled neuron model performance. In terms of experimental content, the study performed data processing on simulated signals and vibration signals of gearbox bearing faults collected in the laboratory environment. By comparing the coupled neuron model optimized with a reinforcement learning algorithm, particle swarm algorithm, and quantum particle swarm algorithm, the experimental results show that the coupled neuron model optimized with a deep reinforcement learning algorithm has the optimal signal-to-noise ratio of the output signal and recognition rate of the bearing faults, which are −13.0407 dB and 100%, respectively. The method shows significant performance advantages in realizing the energy enhancement of the bearing fault eigenfrequency and provides a more efficient and accurate solution for bearing fault diagnosis, which has important engineering application value.

When acquiring point cloud data of precision parts using 3D scanning devices, occlusion or equipment limitations often lead to sparse and incomplete data, resulting in the distortion or loss of key geometric features. To address this issue, this study proposes an attention-enhanced feature-based point cloud completion network for precision parts, using precision bearing rings as an example to construct a dedicated completion dataset for training. The proposed network adopts an encoder–decoder architecture. In the encoder stage, a curvature-weighted sampling feature extraction module and spatial attention mechanism are introduced to extract both local and global features from the incomplete point cloud, followed by multilevel feature fusion. The multiscale features extracted by the encoder are then fed into the decoder, which hierarchically and progressively predicts the missing regions of the point cloud. Finally, an adversarial generation module incorporating a biased attention mechanism enhances the sensitivity of the network to geometric structural differences, thereby producing a complete and refined point cloud as the final output. Experimental results show that on the ShapeNet-part dataset, the proposed network achieves average CD, Pred → GT, and GT → Pred errors of 4.663, 2.459, and 2.457, respectively, representing reductions of 10.8%, 4.7%, and 8.1%, respectively, compared with the mainstream PF-Net completion network. On the bearing ring dataset constructed in this study, the average CD, Pred → GT, and GT → Pred errors were 0.497, 1.064, and 0.601, respectively, decreasing by 9.3%, 16.3%, and 16.2%, respectively, relative to PF-Net. Moreover, the proposed network effectively completed the point clouds of various missing parts, demonstrating its robustness across different types of precision parts.

To address the issue that sparse point cloud maps constructed by SLAM cannot provide detailed information about measured objects, and image sequence-based measurement methods have problems with large data volume and cumulative errors, this paper proposes a scene measurement method that integrates image sequences with an improved LiDAR SLAM. By introducing plane features, the positioning accuracy of LiDAR SLAM is enhanced, and real-time odometry poses are generated. Simultaneously, the system captures image sequences of the measured object using synchronized cameras, and NeRF is used for 3D reconstruction. Time synchronization and data registration between the LiDAR and camera data frames with identical timestamps are achieved. Finally, the least squares method and ICP algorithm are employed to compute the scale factor s and transformation matrices R and t between different point clouds from LiDAR and NeRF reconstruction. Then, the precise measurement of the objects could be implemented. Experimental results demonstrate that this method significantly improves measurement accuracy, with an average error within 10 mm and 1°, providing a robust and reliable solution for scene measurement.