The accurate identification of permanent magnet synchronous motor (PMSM) parameters is the basis for high-performance drive control. The traditional PMSM multiparameter identification method experiences problems with the uncertainty of the identification results and low identification accuracy due to the under-ranking of the mathematical model of motor control. A multiparameter identification of PMSM based on a model reference adaptive system and simulated annealing particle swarm optimization (MRAS-SAPSO) is proposed here. The algorithm first identifies the electrical parameters of the PMSM (stator winding resistance R, cross-axis inductance L, and magnetic linkage ψ_f) by means of the model reference adaptive system method. Second, the result is used as the initial population in particle swarm optimization identification to further optimize and identify the electrical and mechanical parameters (moment of inertia J and damping coefficient B) in the motor control system. Additionally, in order to avoid problems such as premature convergence of the particle swarm in the optimization search process, the results of the adaptive simulated annealing algorithm to optimize multiparameter identification are introduced. The simulation experiment results show that the five identification parameters obtained by the MRAS-SAPSO algorithm are highly accurate and stable, and the errors between them and the real values are below 2%. This also verifies the effectiveness and reliability of this identification method.

The large size tolerance and positional differences of burrs in cast iron blanks make it easy for traditional teaching polishing paths to cause overcutting or undercutting. Rapid and accurate identification of burrs and real‐time correction of polishing trajectories are key technical issues for achieving high‐precision polishing. Here, a deep learning‐based method for defect detection in cast iron parts and surfaces is proposed. Firstly, a self‐made dataset of cast iron parts and surface defects is created and annotated, and a variety of data augmentation methods are used to expand the number of samples in the original dataset, alleviating the problem of small sample size. Then, the coordinate attention mechanism is introduced into the backbone network to allocate more attention to the defect target. Finally, the bidirectional weighted feature pyramid network (BiFPN) is used in the feature fusion network to replace the original path aggregation network, improving the model's ability to fuse features of different sizes. Experimental results show that compared with the original model, the mean average precision (mAP) is increased by 3.1%, and the average precision (AP) in defect classification is increased by 7.6%, with an FPS of 112, achieving accurate and efficient real‐time detection of cast iron parts and surface defects.

Background: Infectious diarrhea remains a major public health problem worldwide. This study used stacking ensemble to developed a predictive model for the incidence of infectious diarrhea, aiming to achieve better prediction performance. Methods: Based on the surveillance data of infectious diarrhea cases, relevant symptoms and meteorological factors of Guangzhou from 2016 to 2021, we developed four base prediction models using artificial neural networks (ANN), Long Short-Term Memory networks (LSTM), support vector regression (SVR) and extreme gradient boosting regression trees (XGBoost), which were then ensembled using stacking to obtain the final prediction model. All the models were evaluated with three metrics: mean absolute percentage error (MAPE), root mean square error (RMSE), and mean absolute error (MAE). Results: Base models that incorporated symptom surveillance data and weekly number of infectious diarrhea cases were able to achieve lower RMSEs, MAEs, and MAPEs than models that added meteorological data and weekly number of infectious diarrhea cases. The LSTM had the best prediction performance among the four base models, and its RMSE, MAE, and MAPE were: 84.85, 57.50 and 15.92%, respectively. The stacking ensembled model outperformed the four base models, whose RMSE, MAE, and MAPE were 75.82, 55.93, and 15.70%, respectively. Conclusions: The incorporation of symptom surveillance data could improve the predictive accuracy of infectious diarrhea prediction models, and symptom surveillance data was more effective than meteorological data in enhancing model performance. Using stacking to combine multiple prediction models were able to alleviate the difficulty in selecting the optimal model, and could obtain a model with better performance than base models.

Aiming at the problems of low detection accuracy, high computational complexity and long‐time consumption of visual perception model in a complex mining environment, this research designs a visual information perception system of coal mine comprehensive excavation working face for an edge computing terminal. Firstly, the C3‐Fast feature extraction module, spatial pyramid pooling with cross‐stage partial connection (SPPCSPC) pooling module, bi‐directional feature pyramid network and lightweight decoupled detection head are used to optimize the YOLOv5s model, so as to construct the FSBD‐YOLOv5s multi‐object detection model. Secondly, the pruning and distillation algorithm is used to lighten the FSBD‐YOLOv5s model, and the model complexity is greatly reduced while maintaining the model detection accuracy. Further, the lightweight FSBD‐YOLOv5s model is migrated and deployed to the edge computing terminal platform and the TensorRT engine is used to accelerate model inference. Finally, experiments are carried out based on the data set of the coal mine comprehensive excavation working face. The experimental results show that on the edge computing terminal platform, the parameters and computational volume of the lightweight FSBD‐YOLOv5s model are reduced by 50.8% and 34.0%, while its detection accuracy and speed reach 94.0% and 43.7 fps, which can fully satisfy the requirements of the accuracy and real‐time for the coal mine engineering applications.

At the Institute of Plasma Physics of the Chinese Academy of Sciences, a design of the pencil beam scanning nozzle is being planned. The main goal of the design is to meet the requirements of the radiation field and the scanning speed of the superconducting accelerators SC200 and to achieve a compact structure. Scanning magnets are one of the core components in the pencil beam scanning system and used to control the trajectory of the proton beam to form a radiation field to be tumor shape. This paper mainly discusses the physical considerations and requirements of the scanning system and scanning electromagnetic design. The tapered air gap of scanning magnet Y was used to accommodate the deflection envelope of the scanning magnet X. Since the two scanning magnets are excited by alternating currents and the maximum repetition frequency are up to 50 Hz and 12.5 Hz, respectively, eddy currents and losses are expected to be significant. To study the eddy current effect, the eddy current and steady-state thermal simulation of the magnet end plate were carried out, and the results of the simulation were discussed.

To improve the roadway adaptability and control accuracy of anchoring equipment, a stepping anchoring device was designed. A permanent-magnet synchronous motor control and a harmonic suppression algorithm were integrated to optimize the dynamic control system of stepping-type anchoring equipment. The results of an experimental simulation and analysis showed that when the coefficient of coal rock hardness f = 5, 6, and 7, the pulsation coefficient of the hydraulic pump outlet pressure, hydraulic motor output speed, and pump-controlled hydraulic cylinder advance speed in the hydraulic circuit of a pump-controlled motor did not exceed 3% after the equipment based on sliding mode control (SMC) entered the steady state, while the maximum pulsation coefficient was only 32.5% of the PI control. Based on the SMC, the harmonic components of the permanent magnet synchronous motor in the power system were suppressed and compensated for. This enhanced the stiffness of the hydraulic system under motor drive. When the rock stiffness factor gradually changed from f = 5 to f = 8 and increased suddenly from f = 5 to f = 6, the pressure overshoot at the outlet of the hydraulic pump of the pump-controlled motor system was reduced from 11.19% to 7.97% and from 61.19% to 52.88%, respectively, compared with that before the optimization. It was thereby proven that SMC based on harmonic suppression can effectively reduce the system pulsation caused by the multi-factor coupling of anchoring equipment and provide technical support for the optimal control of the power system of stepping-type anchoring equipment.