Zewen Liu

In circular production lines, issues such as positional errors, manufacturing errors at different square groove workstations, and the accumulation of errors during continuous assembly reduce the assembly success rate and limit efficiency. To address these challenges in assembling square groove parts, this study focuses on the jamming and wedging problems encountered during the assembly of square grooves and square parts. It analyzes typical assembly hole searching contact situations and proposes corresponding strategies. Based on the relative geometric relationships between the assembly workpieces, the entire assembly process is divided into three stages: pre-assembly, hole search contact adjustment, and insertion. Due to the complexity of predicting assembly forces and the uncertainty of workstation assembly in circular production lines, this study emphasizes the hole search contact adjustment stage. An innovative vertical hole search strategy is proposed and compared with the Archimedes spiral search method. This strategy models the contact between the end effector and the environment as a mass–damping–spring second-order system, achieving compliant assembly of square holes through admittance control. By analyzing the admittance parameters using control variables, the optimal admittance parameters are determined, and the admittance parameter pattern is applied in the experiments. Experimental results on the square hole assembly platform show that, under the optimal admittance parameters, the vertical hole search strategy significantly reduces search time and improves efficiency. Compared to the traditional Archimedes spiral hole search strategy, the average search adjustment time was increased by 5.8 s, improving efficiency by 46.4%, and the desired assembly outcomes were achieved.

Visual inspection detects manual assembly actions to improve quality. Existing methods mainly analyze behaviors in single assembly scenarios using action recognition algorithms, but they cannot adapt to dynamic product switching and varying station environments in manual assembly lines. This paper proposes an adaptive assembly inspection method based on hand motion trajectories. By constructing an assembly inspection model based on the "Component-Tool-Product" triplet, the YOLOv9 model is employed to capture the spatiotemporal hand trajectory data stream. The assembly process is divided into a sequence of transitions between different assembly regions based on the hand's trajectory. The system analyzes the real-time hand trajectories using Dynamic Time Warping (DTW) and dwell time algorithms to obtain real-time assembly flow, allowing for the detection of missed and misassembled components. Additionally, the frame difference method is introduced to extract hand motion features, and an Attention Feature Fusion (AFF) module is used to integrate multi-scale features with motion texture information, enhancing the performance of the object detection model. Experimental results show that the proposed algorithm effectively reduces the false detection rate, with an average detection accuracy of 96% for missed and misassembled behaviors. The improved YOLOv9 model achieves an mAP@0.5 of 93.94%.

The deployment of a manufacturing execution system (MES) holds promising potential in facilitating the accumulation of a substantial amount of inspection data. Low quality levels in discrete manufacturing environments are the result of multi-factor coupling and the failure to detect quality issues promptly in accordance with manufacturing settings, which may trigger the propagation of downstream defects. Currently, most inspection quality methods consist of direct measurements followed by manual judgment. The integration of deep learning methods provides a feasible way in which to identify defects on time, thus improving the acceptance rate of factories. This paper focuses on the design of a data-driven quality prediction and control model, built around discrete manufacturing characteristics, and uses fuzzy theory to evaluate the quality levels of production stages. Furthermore, a multivariate long- and short-term memory sequence model is proposed in order to explore the qualitative information from time domain features. The data regarding the produced water dispensers are validated using three evaluation indices, namely, RMSE, MAE, and MAPE. The results indicate that the multivariate long- and short-term memory model exhibits stronger prediction performance.