As a highly automated carrying vehicle, an automated guided vehicle (AGV) has been widely applied in various industrial areas. The collision avoidance of AGV is always a problem in factories. Current solutions such as inertial and laser guiding have low flexibility and high environmental requirements. An INS (inertial navigation system)-UWB (ultra-wide band) based AGV collision avoidance system is introduced to improve the safety and flexibility of AGV in factories. An electronic map of the factory is established and the UWB anchor nodes are deployed in order to realize an accurate positioning. The extended Kalman filter (EKF) scheme that combines UWB with INS data is used to improve the localization accuracy. The current location of AGV and its motion state data are used to predict its next position, decrease the effect of control delay of AGV and avoid collisions among AGVs. Finally, experiments are given to show that the EKF scheme can get accurate position estimation and the collisions among AGVs can be detected and avoided in time.

High-dimensional data often contain noisy and redundant features, posing challenges for accurate and efficient feature selection. To address this, a dynamic multitask learning framework is proposed, which integrates competitive learning and knowledge transfer within an evolutionary optimization setting. The framework begins by generating two complementary tasks through a multi-criteria strategy that combines multiple feature relevance indicators, ensuring both global comprehensiveness and local focus. These tasks are optimized in parallel using a competitive particle swarm optimization algorithm enhanced with hierarchical elite learning, where each particle learns from both winners and elite individuals to avoid premature convergence. To further improve optimization efficiency and diversity, a probabilistic elite-based knowledge transfer mechanism is introduced, allowing particles to selectively learn from elite solutions across tasks. Experimental results on 13 high-dimensional benchmark datasets demonstrate that the proposed algorithm achieves superior classification accuracy with fewer selected features compared to several state-of-the-art methods. Across 13 benchmarks, the proposed method achieves the highest accuracy on 11 out of 13 datasets and the fewest features on eight out of 13, with an average accuracy of 87.24% and an average dimensionality reduction of 96.2% (median 200 selected features), clearly validating its effectiveness in balancing exploration, exploitation, and knowledge sharing for robust feature selection.

As the most popular renewable energy, solar energy could be converted into electricity by photovoltaic (PV) systems directly. To maximize the effectiveness of the conversion, it is critical to find the precise and accurate parameters of the PV model. In this paper, we propose a level‐based learning swarm optimizer with stochastic fractal search (LLSOF) to tackle the parameter estimation of several kinds of solar PV models. The population is separated into multiple levels according to their fitness at first. The individuals at the lower levels evolve through learning from the individuals at the higher levels. Benefiting from the interactive learning among levels, the population could approach the multiple optimal regions rapidly. To enhance the local search ability, stochastic fractal search is introduced to locate the optima accurately. Combination of both, the proposed LLSOF could achieve a good balance on both exploration and exploitation. To evaluate the performance of LLSOF, it is used to obtain the parameters of three PV models and compared with nine well‐established algorithms. Comparative results validate the excellent performance of LLSOF. Moreover, the application manufactory’s data sheets report the superior efficiency and effectiveness of LLSOF for the parameter estimation of PV systems.

The width of the tobacco filament (WTF) is a significant process parameter in cigarette production as it has a crucial impact on both the physical quality and sensory experience of the product. The detection methods currently employed for WTF mainly involve manual visual inspection or low-frequency offline inspection, which lack representation, accuracy, and efficiency. To enhance the detection efficiency and accuracy, a method for detecting WTF images utilizing the coordinate point fitting method (CPFM) is proposed. We compare the performance of CPFM with the conventional Hough transform method (HTM) and the circle with different radii method (CDRM). Based on experimental results, CPFM has a relative error of 5.3%, an absolute error of 0.085 mm, and a maximum relative standard deviation of 1% in six repetitive experiments. This suggests that the suggested CPFM technique is dependable and dependable and fulfills the statistical demands of metrology. By implementing the WTF image detection method, which relies on the coordinate point fitting methodology, detection efficiency and accuracy are substantially increased. The technique necessitates rapid and exact WTF detection and surpasses prior approaches significantly. Compared to traditional methods, the CPFM method exhibits distinct benefits in detecting WTF. It is probable that the method will become widely used in cigarette production to improve both product quality and production efficiency.