To address path conflicts, lagging dynamic response, and multi-objective optimization in multi-AGV systems for circuit breaker manufacturing, this paper proposes a digital twin (DT)-driven collaborative path planning method integrating improved ant colony algorithm (IACO) and multi-agent deep reinforcement learning (MADDPG). A four-layer DT architecture is constructed to enable bidirectional real-time mapping between physical and virtual entities. Based on a mathematical model minimizing completion time, energy, and load balance, a hierarchical strategy is designed: the upper-layer IACO handles global planning, while the lower-layer MADDPG manages dynamic obstacle avoidance. Simulation results show that the IACO-MADDPG hybrid reduces task time by 14.9% compared to traditional ACO. In dynamic scenarios with 30% sudden tasks, it achieves an 85.2 ms response time and 98.7% completion rate. This approach effectively enhances scheduling efficiency and system stability in intelligent workshops.

The conventional calibration of motor starter delay characteristics is often hampered by excessive reliance on manual expertise, limited accuracy, and low efficiency. To address these issues, this paper proposes an intelligent computational method that integrates multiple advanced algorithms for predicting the tripping time and determining the optimal correction amount of the threaded adjusting component. The approach first employs a Temporal Optimized Attention Convolutional Neural Network (TOA-CNN) to dynamically extract temporal features from the starting process. Subsequently, a Physics-Informed Neural Network combined with a Metaheuristic Collaborative optimization model (PINN-MC) is constructed, which deeply integrates the physical mechanism of thermal deformation with data-driven compensation to achieve high-precision prediction of the tripping time. Finally, the Multi-Objective Salp Swarm Algorithm (MOSSA) is adopted to perform multi-objective collaborative optimization of the thread correction amount, ensuring accuracy while balancing adjustment cost. Experimental results demonstrate that the proposed method significantly improves prediction accuracy and the first-pass calibration success rate, providing reliable intelligent decision support for the precise and efficient calibration of motor starters.

Conventional overload verification of bimetallic protection elements requires long-duration current loading and considerable time and energy consumption. This study proposes a rapid verification method combining a first-order thermodynamic equivalence model with image-based deflection measurement. Local linear interpolation between adjacent measured frames was used to determine the energization time corresponding to a prescribed target deflection. A current-dependent empirical correction factor was introduced to compensate for systematic deviations caused by simplified lumped thermal parameters and test-specific thermal boundary conditions. The model was identified using one target-deflection dataset and evaluated at two additional target deflections without parameter re-identification. Repeated tests were also conducted to assess cycle-to-cycle stability. The results show that the corrected model substantially reduced the temperature-rise deviation, maintained good prediction consistency across different target deflections, and exhibited low cycle-to-cycle variability. The method provides a physics-informed semi-empirical framework for rapid evaluation of bimetallic-strip overload characteristics. Further re-identification and assembled-product validation are required when the specimen configuration or thermal boundary conditions change.

Intradialytic hypotension (IDH) is a common complication of hemodialysis and is associated with treatment interruption, reduced patient tolerance, cardiovascular events, and hospitalization. Existing machine learning studies often use only limited dynamic dialysis information and provide insufficient feature interpretation. This study proposes an IDH risk prediction method based on multi-domain dynamic features and an improved Sparrow Search Algorithm (ISSA). After temporal alignment, outlier handling, and missing-value imputation, a candidate feature set was constructed from 12 baseline variables and 48 time-domain, frequency-domain, and time–frequency-domain features extracted from six continuous dialysis parameters. ISSA was then used to select a 13-dimensional feature subset comprising eight baseline and five dynamic features. Several machine learning models were evaluated before and after feature selection. Using a public hemodialysis monitoring dataset from a tertiary medical center, XGBoost achieved the best overall performance. Adding the five selected dynamic features increased ROC-AUC from 0.8355 to 0.8410 (ΔAUC = 0.0055, 95% CI: 0.0010–0.0100, p = 0.020), indicating a statistically significant incremental contribution. TreeSHAP analysis identified the spectral centroid of dialysis duration, conductivity, dialysate temperature, dialysis duration, and pre-dialysis body weight as important predictors. The proposed framework supports compact and interpretable early IDH risk prediction.