Search

Achieving precise and robust control in dynamic environments remains a challenge, particularly in nonlinear and uncertain systems. This paper proposes a novel two-layer intelligent learning control framework to address these issues, integrating an output recurrent fuzzy neural long short-term memory broad learning system (ORFNLSTM-BLS) with a root mean squared propagation (RMSprop) optimization algorithm. The first layer focuses on real-time system identification, leveraging ORFNLSTM-BLS to learn complex nonlinear system dynamics and effectively capture long-term dependencies in sequential data. The second layer implements an intelligent adaptive controller based on the ORFNLSTM-BLS, which dynamically adjusts control actions for time-varying setpoint tracking and disturbance rejection. The RMSprop optimization algorithm is applied across both layers to adaptively regulate learning rates, ensuring faster convergence and mitigating gradient issues. The convergence of the proposed method is provided through five theorems, ensuring gradient boundedness and learning rate conditions. Simulation and experimental results validate that, compared to conventional PID, the proposed method achieves superior tracking accuracy, with the best case showing an 82% reduction in RMSE, and enhanced control efficiency, with an 85% reduction in ITAE. Additionally, computational analysis shows a 10% increase in processing time for SISO tasks and 84% for MIMO cases. Despite the higher complexity, the method remains feasible for real-time applications. This work advances intelligent control systems, offering a robust solution for environments with sequential data and uncertainties.

Abstract The understanding that students on varsity baseball teams exhibit lower academic performance amid the growth of baseball in Taiwan is well established. However, some studies have indicated a positive correlation between sports participation and academic achievement. Therefore, this study delved into the causal relationships between baseball-team participation and academic performance among ninth-grade students in Taiwan. It further explored the influence of various background factors based on the three facets of family capital on their academic performance. Data collected from an education longitudinal survey of secondary school students. Through bivariate analysis, factor analysis, and multiple regression analysis, the following findings emerged: (a) Baseball-team students exhibited 47.5 points lower academic performance than non-baseball-team ones. (b)The low academic performance was not exclusively a result of the poorer academic performance of indigenous students. (c)The hypothesis that three dimensions of family capital impact on academic performance was supported. (d) Baseball-team participation contributed to the low academic performance, which was not caused by the low eighth-grade results of the students. They exhibited low BCT scores after their 8th-grade results was controlled.

This paper proposes a novel adaptive predictive Proportional-Integral-Derivative (PID) controller utilizing an output recurrent fuzzy broad learning systems (ORFBLS) for Multiple-Input Multiple-Output (MIMO) digital control systems, aiming to effectively adapt to changing setpoints and dynamic environments. The proposed controller, MIMO ORFBLS-APPID controller in short, is proposed to extend the application of ORFBLS as an adaptive adjustment mechanism for PID gains parameters, where the controller gain matrices are automatically tuned over time by employing the Jacobian transformations of the MIMO ORFBLS identifier. Three theorems are established to ensure proper usage and successful applications of the proposed controller. The setpoints tracking control performance and disturbance rejection abilities are firmly illustrated by performing three simulations to the multivariable nonlinear dynamic systems. Moreover, one experimental study to the laboratory-built extrusion barrel in a plastic injection molding machine is done to validate the effectiveness and practicality of the proposed control method. Through comparative simulations and experimental results, the proposed controller has been shown to outperform two existing control methods in terms of control performance indexes.

We report the effects of gold nanoparticles (GNP) on the enhancement of the dose effect and double-strand break (DSB) induction for X-ray monoenergies (10 keV–2 MeV). The overall relative biological effectiveness (RBE) was defined as the product of dose and DSB enhancement. The cellular doses and energy spectra were computed using the PENELOPE (PENetration and Energy LOss of Positrons and Electrons) code. The DNA damage yields were estimated using the MCDS (Monte Carlo damage simulation) code. Considering the production of Auger electrons induced by 7mg/ml GNP, we found that dose enhancement at the 30 keV was ~4.0 for cells with radius $4~\mu \text{m}$ . The DSB induction increased as GNP concentrations increased and was dependent on X-ray energy. These findings demonstrated that the maximum RBE was attained at 30–40 keV and therefore this energy range would be more efficient in cancer cell killing.

This paper presents a novel real-time collision-free speed alteration strategy using a danger index and an elite real-coded genetic algorithm (ERGA) for environments in which humans and robots coexist or cooperate, in order to guarantee the safety of an operator who works with a collaborative robot. A danger index based on ellipsoid modeling of the operator and robot describes the degree of safety during human-robot interactions. The ERGA and a penalty function are used to solve the constrained nonlinear optimization problem to change the handling speed of the robot. Comparative simulation results show the superiority of the proposed method by comparing to two existing methods. The applicability of the proposed method is verified using two experiments involving a 6-DoF industrial manipulator with an EtherCAT network protocol, an RGB-D sensor and a real-time operation system.

This paper presents an intelligent solider combat training (ISCT) system using X-Box Kinect and augmented virtual reality (AVR) to improve soldier training performance through AVR-based simulation combat fields. In this human-machine interactive system, a systematic design and mechatronic approach is used to construct the overall system structure. The Kinect detects soldiers’ positions and postures, situating them in interactive combat soldier training courses. Experimental results demonstrate the effectiveness and applicability of the proposed method.