Ali Rospawan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Ali Rospawan has a total of 22 co-authors. Here are the top co-authors by number of shared publications:
- Ching-Chih Tsai
Department of Electrical Engineering, National Chung Hsing University, Taichung, Taiwan
10 shared publications - Chi-Chih Hung
Department of Electrical Engineering, National Chung Hsing University, Taichung, Taiwan
3 shared publications Chi-Hsiang Li
Department of Electrical Engineering, National Chung Hsing University, Taichung, Taiwan
2 shared publications- Guo-Hwa Yang
National Chung Hsing University
2 shared publications Aan Febriansyah
Department of Electronic Engineering, Politeknik Manufaktur Negeri Bangka Belitung
1 shared publicationBo-Wei Chen
National Chung Hsing University
1 shared publication
Latest Publications
- 16 October 2026
- Published by Elsevier in ISA Transactions
Intelligent adaptive MIMO predictive control using stacked polynomial fuzzy broad learning systems
- 16 October 2026
- Published by Elsevier in ISA Transactions
Intelligent adaptive MIMO predictive control using stacked polynomial fuzzy broad learning systems
- 30 September 2026
- Published by Wiley in Asian Journal of Control
Intelligent Industrial Setpoint Tracking Control Using Output Recurrent Elliptic Fuzzy Broad Learning System
This paper proposes an intelligent industrial setpoint tracking control approach using an output recurrent elliptic fuzzy broad learning system (Elliptic ORFBLS). This approach integrates the strengths of intelligent control, which effectively manages complex nonlinear systems with an adaptive identification mechanism that efficiently handles uncertain parameters in unknown systems. The adaptive mechanism notably enhances transient state responses, leading to faster rise times and reduced overshoot, while ensuring stable and precise setpoint tracking in the steady state. Three theorems are presented to guarantee system convergence, stability, and applicability. Additionally, a comprehensive study on time complexity and memory consumption is included to assist practitioners in controller selection. Through comparative simulations and experimental validations, this control strategy is shown to offer a robust and effective solution for challenging nonlinear systems.
- 30 September 2026
- Published by Wiley in Asian Journal of Control
Intelligent Industrial Setpoint Tracking Control Using Output Recurrent Elliptic Fuzzy Broad Learning System
This paper proposes an intelligent industrial setpoint tracking control approach using an output recurrent elliptic fuzzy broad learning system (Elliptic ORFBLS). This approach integrates the strengths of intelligent control, which effectively manages complex nonlinear systems with an adaptive identification mechanism that efficiently handles uncertain parameters in unknown systems. The adaptive mechanism notably enhances transient state responses, leading to faster rise times and reduced overshoot, while ensuring stable and precise setpoint tracking in the steady state. Three theorems are presented to guarantee system convergence, stability, and applicability. Additionally, a comprehensive study on time complexity and memory consumption is included to assist practitioners in controller selection. Through comparative simulations and experimental validations, this control strategy is shown to offer a robust and effective solution for challenging nonlinear systems.
- Open Access
- 31 July 2026
- Published by National Research and Innovation Agency in Journal of Mechatronics, Electrical Power, and Vehicular Technology
- Vol. 17 (1) , 194-205
Adaptive PID control using TSK elliptic fuzzy and static feedforward for observable disturbance rejection in industrial heating ovens
This paper presents an advanced control strategy aimed at accelerating the temperature recovery time in industrial heating ovens, particularly in response to observable disturbances such as periodic door openings. The proposed method combines a Takagi-Sugeno-Kang (TSK) elliptic fuzzy-based adaptive proportional-integral-derivative (PID) control with a static feedforward (FF) control strategy. The TSK elliptic fuzzy system models the input-output dynamics and adaptively adjusts the PID gains, allowing the controller to respond effectively to varying system conditions. The static feedforward control is designed to specifically counteract the measurable disturbances to shorten recovery time and improve stability. The strategy is validated through both simulation and experiment on a low-cost STM32 microcontroller. Compared with a conventional PID controller, it reduced the RMSE by 32.27 % and the ISE by 54.13 %, together with a recovery time shortened by approximately 72 s, reflecting the faster disturbance recovery achieved by the static feedforward action. Experimental results confirmed these findings, with a higher feedforward gain further reducing the temperature drop and accelerating recovery. The proposed technique offers a reliable and practical solution for practitioners in managing similar disturbance patterns in industrial settings.
- 31 July 2026
- Published by National Research and Innovation Agency in Journal of Mechatronics, Electrical Power, and Vehicular Technology
- Vol. 17 (1) , 194-205
Open AccessAdaptive PID control using TSK elliptic fuzzy and static feedforward for observable disturbance rejection in industrial heating ovens
This paper presents an advanced control strategy aimed at accelerating the temperature recovery time in industrial heating ovens, particularly in response to observable disturbances such as periodic door openings. The proposed method combines a Takagi-Sugeno-Kang (TSK) elliptic fuzzy-based adaptive proportional-integral-derivative (PID) control with a static feedforward (FF) control strategy. The TSK elliptic fuzzy system models the input-output dynamics and adaptively adjusts the PID gains, allowing the controller to respond effectively to varying system conditions. The static feedforward control is designed to specifically counteract the measurable disturbances to shorten recovery time and improve stability. The strategy is validated through both simulation and experiment on a low-cost STM32 microcontroller. Compared with a conventional PID controller, it reduced the RMSE by 32.27 % and the ISE by 54.13 %, together with a recovery time shortened by approximately 72 s, reflecting the faster disturbance recovery achieved by the static feedforward action. Experimental results confirmed these findings, with a higher feedforward gain further reducing the temperature drop and accelerating recovery. The proposed technique offers a reliable and practical solution for practitioners in managing similar disturbance patterns in industrial settings.
- 27 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. PP (1530437X) , 1
Enhanced RGB-D Visual SLAM Using Photogrammetric Key-Frame Selection Method and Static Conditional Probability Model
The original ORB-SLAM3 has been designed with static backgrounds in mind. However, when dealing with moving obstacles in a dynamic environment, this method could lead to significant localization errors and inaccuracies in the generated maps. This paper presents an enhanced ORB-SLAM3 method to mitigate these errors caused by dynamic environments and moving obstacles. To achieve this, we integrate the known Photogrammetric Key-Frame Selection (PKS) algorithm to optimize keyframe selection, and a Static Conditional Probability Model (SCPM) for effective identification and eliminating dynamic map points in each frame. Extensive evaluation simulations demonstrate that our approach substantially reduces Absolute Trajectory Error (ATE) metrics compared to the original ORB-SLAM3, with details as follows; mean ATE by 84% on TUM datasets and 17.91% in Gazebo simulations, median ATE by 86% and 28.19%, root mean squared error (RMSE) of ATE by 80% and 29.45%, and standard deviation (STD) of ATE by 71.5% and 61.73%, respectively. This performance improvement comes with a modest computational cost increase of 12.5% on TUM datasets and 31% in Gazebo environments. Furthermore, the experimental validation with an autonomous mobile robot (AMR) in dynamic indoor environments further demonstrates that the proposed enhanced ORB-SLAM3 method achieves superior accuracy, performance, and robustness, with 51.56%, 33.49%, 27.46%, and 9.99% of improvement in terms of mean, median, RMSE and STD of ATE, making it particularly valuable for real-world robotic applications in crowded settings.
- 27 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. PP (1530437X) , 1
Enhanced RGB-D Visual SLAM Using Photogrammetric Key-Frame Selection Method and Static Conditional Probability Model
The original ORB-SLAM3 has been designed with static backgrounds in mind. However, when dealing with moving obstacles in a dynamic environment, this method could lead to significant localization errors and inaccuracies in the generated maps. This paper presents an enhanced ORB-SLAM3 method to mitigate these errors caused by dynamic environments and moving obstacles. To achieve this, we integrate the known Photogrammetric Key-Frame Selection (PKS) algorithm to optimize keyframe selection, and a Static Conditional Probability Model (SCPM) for effective identification and eliminating dynamic map points in each frame. Extensive evaluation simulations demonstrate that our approach substantially reduces Absolute Trajectory Error (ATE) metrics compared to the original ORB-SLAM3, with details as follows; mean ATE by 84% on TUM datasets and 17.91% in Gazebo simulations, median ATE by 86% and 28.19%, root mean squared error (RMSE) of ATE by 80% and 29.45%, and standard deviation (STD) of ATE by 71.5% and 61.73%, respectively. This performance improvement comes with a modest computational cost increase of 12.5% on TUM datasets and 31% in Gazebo environments. Furthermore, the experimental validation with an autonomous mobile robot (AMR) in dynamic indoor environments further demonstrates that the proposed enhanced ORB-SLAM3 method achieves superior accuracy, performance, and robustness, with 51.56%, 33.49%, 27.46%, and 9.99% of improvement in terms of mean, median, RMSE and STD of ATE, making it particularly valuable for real-world robotic applications in crowded settings.
- Open Access
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 105456-105467
Hybrid Navigation of Autonomous Mobile Robots With Two Swerve Wheels in Complex and Confined Environments
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 105456-105467
Open AccessHybrid Navigation of Autonomous Mobile Robots With Two Swerve Wheels in Complex and Confined Environments
- Open Access
- 20 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 34334-34349
Two-Layer Intelligent Learning Control Using Output Recurrent Fuzzy Neural Long Short-Term Memory Broad Learning System With RMSprop
This paper presents a novel two-layer intelligent learning control framework using an output recurrent fuzzy neural LSTM broad learning system (ORFNLSTM-BLS) and a RMSprop optimization algorithm, designed to enhance learning capability and address the limitations of existing fuzzy BLS approaches. 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. Additionally, a comprehensive study on time complexity and memory consumption is presented to guide controller board selection. Simulations and experimental results demonstrate the superiority of the proposed framework in achieving accurate control performance, robustness under uncertainty, and real-world applicability, where conventional PID control fails to meet the required system response. This method offers valuable insights for developing advanced intelligent control solutions in dynamic environments involving sequential data and uncertainty.
- 20 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 34334-34349
Open AccessTwo-Layer Intelligent Learning Control Using Output Recurrent Fuzzy Neural Long Short-Term Memory Broad Learning System With RMSprop
This paper presents a novel two-layer intelligent learning control framework using an output recurrent fuzzy neural LSTM broad learning system (ORFNLSTM-BLS) and a RMSprop optimization algorithm, designed to enhance learning capability and address the limitations of existing fuzzy BLS approaches. 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. Additionally, a comprehensive study on time complexity and memory consumption is presented to guide controller board selection. Simulations and experimental results demonstrate the superiority of the proposed framework in achieving accurate control performance, robustness under uncertainty, and real-world applicability, where conventional PID control fails to meet the required system response. This method offers valuable insights for developing advanced intelligent control solutions in dynamic environments involving sequential data and uncertainty.
- 24 June 2024
- Published by Springer Nature in International Journal of Fuzzy Systems
- Vol. 27 (3) , 774-790
Intelligent MIMO ORFBLS-Based Setpoint Tracking Control with Its Application to Temperature Control of an Industrial Extrusion Barrel
- 24 June 2024
- Published by Springer Nature in International Journal of Fuzzy Systems
- Vol. 27 (3) , 774-790
Intelligent MIMO ORFBLS-Based Setpoint Tracking Control with Its Application to Temperature Control of an Industrial Extrusion Barrel