Kaitwanidvilai, Somyot

Preferred name

Alternative Name

Kaitwanidvilai, S.

Main Affiliation

School of Engineering

somyot.ka@kmitl.ac.th

Now showing 1 - 10 of 35

Some of the metrics are blocked by your
consent settings
Robust 2DOF fuzzy gain scheduling control for DC servo speed controller
(2016-11-01)
Chitsanga, Natchanon
;
Kaitwanidvilai, Somyot
This paper proposes a new design method called “robust 2DOF fuzzy gain scheduling control” for a DC servo speed control system. The proposed technique utilizes the basic concept of 2DOF robust loop shaping, whose time-domain specifications are combined during the controller design using a reference model. In addition, the local controllers are fixed- structure robust controllers whose structure can be specified as for a simple controller. A fuzzy approach is adopted in both system identification process and global control structure to accomplish an entirely robust system. Although the design of robust control in a fuzzy system is not easy, genetic algorithms (GAs) simplify the control design problem to design the fuzzy controller such that the average stability margin is minimized. Implementation of a DC servo speed control was adopted to investigate the effectiveness of the proposed controller. As seen from the results, the proposed controller has more robust performance and can be adopted in applications with a wide operating range. © 2016 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.
Some of the metrics are blocked by your
consent settings
Robust voltage stabilization in an isolated wind-diesel power system using pso based-fixed structure H∞ loop shaping control
(2009-07-30)
Vachyirasricirikul, Sitthidet
;
Ngamroo, Issarachai
;
Kaitwanidvilai, Somyot
It is well known that the power system controller designed by H∞ control is complicated, high order and impractical. In power system applications, practical structures such as proportional integral derivative (PID) etc., are widely used, because of their simple structure, less number of tuning parameters and low-order. However, tuning of controller parameters to achieve a good performance and robustness is based on designer's experiences. To overcome this problem, this paper proposes a fixed structure robust H∞ loop shaping control to design Static Var Compensator (SVC) and Automatic Voltage Regulator (AVR) for robust stabilization of voltage fluctuation in an isolated wind-diesel hybrid power system. The structure of the robust controller of SVC and AVR is specified by a PID controller. In the system modeling, a normalized coprime factorization is applied to represent possible unstructured uncertainties in the power system such as variation of system parameters, generating and loading conditions etc. Based on the H∞ loop shaping, the performance and robust stability conditions are formulated as the optimization problem. The particle swarm optimization is applied to solve for PID control parameters of SVC and AVR simultaneously. Simulation studies confirm the control effect and robustness of the proposed control. © 2009 The Institute of Electrical Engineers of Japan.
Some of the metrics are blocked by your
consent settings
Robust loop shaping-fuzzy gain scheduling control of a servo-pneumatic system using particle swarm optimization approach
(2011-01-01)
Kaitwanidvilai, Somyot
;
Olranthichachat, Piyapong
In this paper, a new technique called robust loop shaping-fuzzy gain scheduled control (RLS-FGS) is proposed to design an effective nonlinear controller for a long stroke pneumatic servo system. In our technique, a nonlinear dynamic model of a long stroke pneumatic servo plant is identified by the fuzzy identification method and is used as the plant for our design. The structure of local controllers is selected as PID control which is proven by many research works that this type of control has many advantages such as simple structure, well understanding, and high performance. The proposed technique uses particle swarm optimization (PSO) to find the optimal local controllers which maximize the average stability margin. In addition, performance weighting function which is normally difficult to obtain is automatically determined by PSO. By the proposed technique, the RLS-FGS controller can be designed, and the structure of local controllers is still not complicated. As seen in the simulation and experimental results, our proposed technique is better than the classical gain scheduled PID controller tuned by pole placement and the conventional fuzzy PID controller tuned by ISE method in terms of robust performance. © 2010 Elsevier Ltd. All rights reserved.
Some of the metrics are blocked by your
consent settings
Experimental realization of PSO-based hybrid adaptive sliding mode control for force impedance control systems
(2025-06-01)
Yanyong, Sarucha
;
Kaitwanidvilai, Somyot
This paper presents a practical solution for an adaptive impedance force controller with online learning capabilities, designed to mitigate the effects of inaccuracies in system identification models. The proposed hybrid algorithm addresses the challenges associated with online learning in real-world machines. Additionally, the system demonstrates the ability to adapt to environmental changes, maintaining high-quality performance despite variations. A sliding surface guarantees system stability, while Particle Swarm Optimization (PSO) optimizes impedance parameters, reducing the risk of local minima. The hybrid algorithm also reduces overshoot and undershoot, resulting in faster system responses. Simulation and experimental results demonstrate that the proposed technique outperforms conventional force control systems in terms of learning ability and overall performance.
Some of the metrics are blocked by your
consent settings
Dual-stage Classification Framework for Detecting Rare or Unseen Patterns Based on Novelty Detection and Supervised Learning
(2024-01-01)
Rungtalay, Natthakritta
;
Kaitwanidvilai, Somyot
In this article, we propose a dual-stage classification framework designed for identifying rare or unseen patterns in the hard disk drive (HDD) industrial test process. The proposed framework integrates novelty detection and supervised learning methodologies to effectively address the challenges associated with imbalanced datasets and the detection of infrequent or unseen patterns within continuously changing environments. By employing novelty detection as the first-stage classifier followed by supervised learning as the second-stage classifier, the proposed method demonstrates an increased capacity to adapt to fluctuating environments, consequently enhancing the overall accuracy of process classification in practical manufacturing settings. To strengthen the robustness of novelty detection methods, an ensemble model technique is employed. Notably, the accuracy of the novelty detection methods in the first stage can be further enhanced with the incorporation of supervised learning techniques, particularly when a sufficiently large number of labeled samples are amassed. The proposed method consistently maintains accuracy, even in the face of changing environments, as it demonstrates the ability to adapt to data drift without necessitating the acquisition of new labeled data in the initial stage. This adaptability makes it particularly well suited for managing imbalanced datasets, rendering it highly practical for industrial applications. In a comprehensive case study conducted within the HDD industry, the framework exhibits immediate adaptability to rapidly changing environments while preserving high accuracy. This highlights the practical effectiveness of the proposed dual-stage classification framework in addressing the unique challenges posed by industrial scenarios.
Some of the metrics are blocked by your
consent settings
PSO-Optimized Deep Learning for Ultra-Precise Corrosion Detection on HDD Read/Write Heads
(2025-01-01)
Punyammaree, Chaiwat
;
Kaitwanidvilai, Somyot
This paper presents a novel deep learning approach for automated detection and counting of corrosion pits on Hard Disk Drive (HDD) read/write heads using Scanning Electron Microscopy (SEM) images. A U-Net model optimized via Particle Swarm Optimization (PSO) is developed to enhance segmentation performance by automatically tuning hyperparameters. The methodology includes optimized SEM image acquisition, preprocessing (patch-based subdivision and expert annotation), PSO-driven hyperparameter selection, and post-processing with thresholding and connected component analysis for pit counting. Experimental results demonstrate that the PSO-optimized U-Net significantly outperforms standard U-Net, SegNet, and LinkNet models, achieving an F1-score of 79.60%, an IoU of 86.51%, and an accuracy of 99.77%. Additionally, the proposed method achieves 86.9% counting accuracy, surpassing human experts (72.7%) while processing images 15 times faster (180 seconds vs. 2700 seconds per image). These findings highlight the potential of PSO-optimized deep learning for improving HDD quality control by providing an accurate, efficient, and standardized solution for corrosion pit detection, ultimately reducing the risk of HDD failure and data loss.
Some of the metrics are blocked by your
consent settings
Maximum power point tracking using hybrid fuzzy based p&o and back propagation (BP) neural network for photovoltaic system
(2014-10-01)
Konghuayrob, Poom
;
Kaitwanidvilai, Somyot
Photovoltaic system is one of the most popular renewable energy sources to solve the problem of energy crisis. The important problem of solar PV systems is their low efficiency and nonlinear output characteristics in the changing weather that causes the difficulty in tracking of maximum power. To overcome this problem, this paper proposes “Hybrid Fuzzy based P&O and Back Propagation (BP) neural network” for improving the efficiency and reducing the power oscillation of PV system. The proposed system composes of two parts which are fuzzy based P&O and Neural Network. The fuzzy based P&O is used to find the maximum power point (MPP) while the neural network is used to find the appropriate modulation index (ma). The proposed algorithm is adopted in the AC module flyback inverter in which modulation index (Δma) is used as the control variable to track the MPP of the PV array. Simulation results verify that the proposed technique can effectively track the power from PV system, and is better than the conventional P&O techniques
Some of the metrics are blocked by your
consent settings
Coordinated SVC and AVR for robust voltage control in a hybrid wind-diesel system
(2010-12-01)
Vachirasricirikul, Sitthidet
;
Ngamroo, Issarachai
;
Kaitwanidvilai, Somyot
This paper proposes a robust control of voltage fluctuation due to the variation of reactive loads in an isolated wind-diesel hybrid power system using Static Var Compensator (SVC) and Automatic Voltage Regulator (AVR). The structure of the voltage controller of SVC and AVR is the proportional integral (PI) controller with single input. In the system modeling, a normalized coprime factorization is applied to represent possible unstructured uncertainties in the power system such as variation of system parameters and generating and loading conditions. Based on the H<inf>∞</inf> loop shaping, the performance and robust stability conditions of the control system are formulated as the optimization problem. The genetic algorithm is applied to solve an optimization problem and to achieve PI control parameters of SVC and AVR simultaneously. Simulation studies show the control effect and robustness of the proposed coordinated SVC and AVR. © 2010 Elsevier Ltd. All rights reserved.
Some of the metrics are blocked by your
consent settings
Low-cost microprocessor-based alternating current voltage controller using genetic algorithms and neural network
(2010-07-01)
Kaitwanidvilai, S.
;
Piyarungsan, P.
A low-cost, high-performance microprocessor-based pulse width modulated (PWM) AC voltage controller with a novel harmonic reduction technique is proposed. Genetic algorithm is adopted to evaluate the optimal turn-on and turn-off angles in the PWM pattern such that the total current harmonic distortion is minimised. The evolved angles are only optimised at a desired output voltage. In the proposed design, an artificial neural network trained by sets of optimal angles is utilised, making the designed system applicable to all operating points. The simulation and experimental results verify that the proposed technique is a suitable technique, and its performance is comparable to the conventional techniques. © 2010 © The Institution of Engineering and Technology.
Some of the metrics are blocked by your
consent settings
Sensor Fusion of Light Detection and Ranging and iBeacon to Enhance Accuracy of Autonomous Mobile Robot in Hard Disk Drive Clean Room Production Line
(2023-01-01)
Yanyong, Sarucha
;
Parichatprecha, Rattapoohm
;
Chaisiri, Punyavee
;
Kaitwanidvilai, Somyot
;
Konghuayrob, Poom
In this paper, the adaptive Monte Carlo localization (AMCL) error in terms of similar data detected by light detection and ranging (LiDAR) in different locations is investigated. This localization causes a robot to move to the incorrect location temporarily. We propose the fusion of landmark-based localization using an iBeacon device combined with the AMCL algorithm. This technique can solve the probabilistic localization problem of the conventional techniques applied in mobile robots by fusing the timed elastic band (TEB) and scan-matching algorithms, which reduces the error from 7 cm to less than 3 cm. The proposed technique is implemented on a clean-room-type mobile robot with 100 kg payload certificated by the SOP39 standard.

Kaitwanidvilai, Somyot

Filters

Settings

Sort By

Results per page