Chanchai Techawatcharapaikul
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Chanchai Techawatcharapaikul has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
- Thanatchai Kulworawanichpong
School of Electrical Engineering Suranaree University of technology Nakhon Ratchasima Thailand
3 shared publications - Banri Khemkladmuk
School of Electrical Engineering Suranaree University of technology Nakhon Ratchasima Thailand
2 shared publications - Pannee Suanpang
Department of Information Technology, Faculty of Science and Technology, Suan Dusit University, Bangkok, Thailand
2 shared publications - Pitchaya Jamjuntr
Electronic and Telecommunication Engineering, Faculty of Engineering, King Mongkut’s University of Technology Thonburi, Bangkok 10140, Thailand
2 shared publications - Atip Doolgindachbaporn
Tony Davies High Voltage Laboratory, University of Southampton, Southampton, U.K.
1 shared publication - Chaiyut Sumpavakup
Research Centre for Combustion Technology and Alternative Energy—CTAE, and College of Industrial Technology, King Mongkut’s University of Technology North Bangkok, Bangkok 10800, Thailand
1 shared publication
Latest Publications
- Open Access
- 9 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 56498-56515
AI-Based Data Fusion of IEC Methods With Dashboard Analytics for Hydrophobicity Evaluation of High-Voltage Insulators
Reliable assessment of insulator surface hydrophobicity is critical for the safety and continuity of power transmission and distribution networks and electrified transportation. While IEC TS 62073 prescribes three established methods—Contact angle(CA), Surface tension(SF), and Spray method(SP) —their deployment is hampered by operator subjectivity, environmental sensitivity, and the lack of an integrated interpretation. We present an AI-assisted, IEC-faithful framework that unifies contact angle, surface tension, and spray method into a single decision pipeline and exposes actionable outputs via a maintenance-oriented dashboard. Methodologically, Contact Angle is automated using Linear Regression Intersection for robust left/right contact estimation; Surface Tension is automated via cotton-tip last-frame and stationery-frame detection to time droplet reformation without manual frame picking; and Spray method leverages Zoning Feature Extraction with k-nearest neighbors, optionally complemented by an SVD–Mahalanobis classifier for borderline cases. Experiments on porcelain type 52-1 insulators under control conditions (30 °C, RH > 70%) comprise 90 droplet sequences for Contact angle, Surface tension and 2,800 Spray method images. As a result, applying these algorithms across the three methods yields interpretation accuracy exceeding 90%. Decision-level fusion improves consistency in intermediate classes while preserving IEC interpretability, and the dashboard provides transparent confidence and trend views for field engineers. In conclusion, the proposed algorithms increase the accuracy and reliability of insulator test interpretation and reduce ambiguity among visually similar features, enabling standards-compliant, reproducible assessments suitable for predictive-maintenance workflows in utilities and rail operations.
- 9 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 56498-56515
Open AccessAI-Based Data Fusion of IEC Methods With Dashboard Analytics for Hydrophobicity Evaluation of High-Voltage Insulators
Reliable assessment of insulator surface hydrophobicity is critical for the safety and continuity of power transmission and distribution networks and electrified transportation. While IEC TS 62073 prescribes three established methods—Contact angle(CA), Surface tension(SF), and Spray method(SP) —their deployment is hampered by operator subjectivity, environmental sensitivity, and the lack of an integrated interpretation. We present an AI-assisted, IEC-faithful framework that unifies contact angle, surface tension, and spray method into a single decision pipeline and exposes actionable outputs via a maintenance-oriented dashboard. Methodologically, Contact Angle is automated using Linear Regression Intersection for robust left/right contact estimation; Surface Tension is automated via cotton-tip last-frame and stationery-frame detection to time droplet reformation without manual frame picking; and Spray method leverages Zoning Feature Extraction with k-nearest neighbors, optionally complemented by an SVD–Mahalanobis classifier for borderline cases. Experiments on porcelain type 52-1 insulators under control conditions (30 °C, RH > 70%) comprise 90 droplet sequences for Contact angle, Surface tension and 2,800 Spray method images. As a result, applying these algorithms across the three methods yields interpretation accuracy exceeding 90%. Decision-level fusion improves consistency in intermediate classes while preserving IEC interpretability, and the dashboard provides transparent confidence and trend views for field engineers. In conclusion, the proposed algorithms increase the accuracy and reliability of insulator test interpretation and reduce ambiguity among visually similar features, enabling standards-compliant, reproducible assessments suitable for predictive-maintenance workflows in utilities and rail operations.
- Open Access
- 1 January 2026
- Published by Institution of Engineering and Technology (IET) in IET Energy Systems Integration
- Vol. 8 (1)
Emergency Power Sharing by Using a Self‐Traction System in a Mass Rapid Transit Railway
Systemwide traction power outages in mass rapid transit systems (MRTSs) can cause trains to stop between stations, leading to service disruption and urgent passenger evacuation requirements. Onboard emergency self‐traction systems (ESTSs) can mitigate this risk by enabling a stranded train to reach the nearest station at low speed. However, installing and maintaining ESTS on every train can increase implementation and lifecycle costs, motivating approaches that can ensure evacuation with partial ESTS deployment. This article introduces a power‐sharing framework for ESTS in an MRTS. The primary aim is to reduce the number of ESTS units needed by facilitating power sharing between trains equipped with ESTS and those without it, while guaranteeing that all trains can safely and quickly evacuate passengers to the nearest station during a systemwide power outage. This study examines the Bangkok Mass Transit System (BTS) Skytrain Silom Line (dark green line) in Thailand, through computer simulation parameterised by real‐world line and operational data, to evaluate the viability of this concept. It analyses variables such as the quantity of trains outfitted with ESTS, the distance from the train to the station where it halted, particular train specifications and additional pertinent aspects. The results reveal that ESTS can efficiently provide backup power to equipped trains and share surplus energy with other trains within the sharing radius with a success rate of 72.41%. This underscores the viability of ESTS operations and aids in the advancement of a more sustainable and efficient MRTS, despite the inherent constraints of ESTS.
- 1 January 2026
- Published by Institution of Engineering and Technology (IET) in IET Energy Systems Integration
- Vol. 8 (1)
Open AccessEmergency Power Sharing by Using a Self‐Traction System in a Mass Rapid Transit Railway
Systemwide traction power outages in mass rapid transit systems (MRTSs) can cause trains to stop between stations, leading to service disruption and urgent passenger evacuation requirements. Onboard emergency self‐traction systems (ESTSs) can mitigate this risk by enabling a stranded train to reach the nearest station at low speed. However, installing and maintaining ESTS on every train can increase implementation and lifecycle costs, motivating approaches that can ensure evacuation with partial ESTS deployment. This article introduces a power‐sharing framework for ESTS in an MRTS. The primary aim is to reduce the number of ESTS units needed by facilitating power sharing between trains equipped with ESTS and those without it, while guaranteeing that all trains can safely and quickly evacuate passengers to the nearest station during a systemwide power outage. This study examines the Bangkok Mass Transit System (BTS) Skytrain Silom Line (dark green line) in Thailand, through computer simulation parameterised by real‐world line and operational data, to evaluate the viability of this concept. It analyses variables such as the quantity of trains outfitted with ESTS, the distance from the train to the station where it halted, particular train specifications and additional pertinent aspects. The results reveal that ESTS can efficiently provide backup power to equipped trains and share surplus energy with other trains within the sharing radius with a success rate of 72.41%. This underscores the viability of ESTS operations and aids in the advancement of a more sustainable and efficient MRTS, despite the inherent constraints of ESTS.
- Open Access
- 24 October 2025
- Published by MDPI AG in Sustainability
- Vol. 17 (21) , 9458
Advancing Sustainable Tourism Through Smart Wheelchair Optimization: A Mixed-Integer Linear Programming Framework for Inclusive Travel
Accessible tourism is a critical aspect of sustainable development, yet many Southeast Asian destinations lack sufficient infrastructure and services for elderly and disabled travelers. This study develops a Mixed-Integer Linear Programming (MILP) framework to optimize travel itineraries, balancing cost, accessibility, and cultural–environmental priorities. A national accessibility database for Thailand was created, encompassing airports, hospitals, public transport nodes, cultural landmarks, and natural attractions. Compared to baseline conventional itineraries—defined as standard travel routes planned without specific accessibility considerations or optimization techniques—the MILP-optimized routes reduce average travel time by 15–20% and improve accessibility scores by 25%. Sensitivity analyses reveal trade-offs between economic efficiency, inclusivity, and infrastructure capacity, while a schematic accessibility network highlights structural fragmentation among airports, hospitals, and secondary attractions. Scenario analyses show that stricter accessibility thresholds improve inclusivity (index: 0.65 to 0.80) but restrict destination options, whereas high-demand scenarios increase costs and reduce inclusivity. A survey of 30 smart wheelchair users indicates high satisfaction with individualized programs and GPS connectivity. These findings underscore the need for investment in multimodal integration, accessibility upgrades, and a national database to enhance inclusive tourism planning. The framework is transferable to other ASEAN countries, contributing to SDG 3, 8, and 11. Overall, this study should be viewed as a prototype or exploratory contribution, with limitations in real-time applicability, generalizability, and implementation of environmental and ethical aspects.
- 24 October 2025
- Published by MDPI AG in Sustainability
- Vol. 17 (21) , 9458
Open AccessAdvancing Sustainable Tourism Through Smart Wheelchair Optimization: A Mixed-Integer Linear Programming Framework for Inclusive Travel
Accessible tourism is a critical aspect of sustainable development, yet many Southeast Asian destinations lack sufficient infrastructure and services for elderly and disabled travelers. This study develops a Mixed-Integer Linear Programming (MILP) framework to optimize travel itineraries, balancing cost, accessibility, and cultural–environmental priorities. A national accessibility database for Thailand was created, encompassing airports, hospitals, public transport nodes, cultural landmarks, and natural attractions. Compared to baseline conventional itineraries—defined as standard travel routes planned without specific accessibility considerations or optimization techniques—the MILP-optimized routes reduce average travel time by 15–20% and improve accessibility scores by 25%. Sensitivity analyses reveal trade-offs between economic efficiency, inclusivity, and infrastructure capacity, while a schematic accessibility network highlights structural fragmentation among airports, hospitals, and secondary attractions. Scenario analyses show that stricter accessibility thresholds improve inclusivity (index: 0.65 to 0.80) but restrict destination options, whereas high-demand scenarios increase costs and reduce inclusivity. A survey of 30 smart wheelchair users indicates high satisfaction with individualized programs and GPS connectivity. These findings underscore the need for investment in multimodal integration, accessibility upgrades, and a national database to enhance inclusive tourism planning. The framework is transferable to other ASEAN countries, contributing to SDG 3, 8, and 11. Overall, this study should be viewed as a prototype or exploratory contribution, with limitations in real-time applicability, generalizability, and implementation of environmental and ethical aspects.
- Open Access
- 1 January 2025
- Published by Institution of Engineering and Technology (IET) in IET Electrical Systems in Transportation
- Vol. 2025 (1)
Optimal Energy Efficiency in a Mass Rapid Transit System Through DC Traction Substation Voltage Control Utilizing Particle Swarm Optimization
This article discusses voltage level modifications in urban mass transit traction substations, focusing on DC railway substations, to reduce power consumption and improve energy efficiency. Substation voltage settings are usually adjusted by a skilled designer using practical judgment and design acumen. To maximize operations, all traction substation voltage levels are automatically adjusted to the same value. This arrangement works well and may not have affected the power supply system. This design often causes operations to deviate from optimal performance, perhaps reducing energy efficiency. This research seeks to determine the optimal traction substation voltage setting that minimizes total energy consumption of DC electric railways. A simulation‐based approach is applied using train movement data and voltage variation scenarios. The proposed designs are linear, V ‐shaped, and fixed‐voltage. Additionally, particle swarm optimization (PSO) is an effective way to find the best design. The Bangkok Transit System (BTS) Sukhumvit line is used for testing. Reduction by the linear framework, energy consumption may be 2.341% lower than the base case. By the PSO, the results in 30 trial test runs suggest a 6.107% energy consumption reduction from baseline.
- 1 January 2025
- Published by Institution of Engineering and Technology (IET) in IET Electrical Systems in Transportation
- Vol. 2025 (1)
Open AccessOptimal Energy Efficiency in a Mass Rapid Transit System Through DC Traction Substation Voltage Control Utilizing Particle Swarm Optimization
This article discusses voltage level modifications in urban mass transit traction substations, focusing on DC railway substations, to reduce power consumption and improve energy efficiency. Substation voltage settings are usually adjusted by a skilled designer using practical judgment and design acumen. To maximize operations, all traction substation voltage levels are automatically adjusted to the same value. This arrangement works well and may not have affected the power supply system. This design often causes operations to deviate from optimal performance, perhaps reducing energy efficiency. This research seeks to determine the optimal traction substation voltage setting that minimizes total energy consumption of DC electric railways. A simulation‐based approach is applied using train movement data and voltage variation scenarios. The proposed designs are linear, V ‐shaped, and fixed‐voltage. Additionally, particle swarm optimization (PSO) is an effective way to find the best design. The Bangkok Transit System (BTS) Sukhumvit line is used for testing. Reduction by the linear framework, energy consumption may be 2.341% lower than the base case. By the PSO, the results in 30 trial test runs suggest a 6.107% energy consumption reduction from baseline.
- Open Access
- 6 October 2024
- Published by MDPI AG in World Electric Vehicle Journal
- Vol. 15 (10) , 453
Adaptive Multi-Agent Reinforcement Learning for Optimizing Dynamic Electric Vehicle Charging Networks in Thailand
The rapid growth of electric vehicles (EVs) necessitates efficient management of dynamic EV charging networks to optimize resource utilization and enhance service reliability. This paper explores the application of adaptive multi-agent reinforcement learning (MARL) to address the complexities of EV charging infrastructure in Thailand. By employing MARL, multiple autonomous agents learn to optimize charging strategies based on real-time data by adapting to fluctuating demand and varying electricity prices. Building upon previous research that applied MARL to static network configurations, this study extends the application to dynamic and real-world scenarios, integrating real-time data to refine agent learning processes and also evaluating the effectiveness of adaptive MARL in maximizing rewards and improving operational efficiency compared to traditional methods. Experimental results indicate that MARL-based strategies increased efficiency by 20% and reduced energy costs by 15% relative to conventional algorithms. Key findings demonstrate the potential of extending MARL in transforming EV charging network management, highlighting its benefits for stakeholders, including EV owners, operators, and utility providers. This research contributes insights into advancing electric mobility and energy management in Thailand through innovative AI-driven approaches. The implications of this study include significant improvements in the reliability and cost-effectiveness of EV charging networks, fostering greater adoption of electric vehicles and supporting sustainable energy initiatives. Future research directions include enhancing MARL adaptability and scalability as well as integrating predictive analytics for proactive network optimization and sustainability. These advancements promise to further refine the efficacy of EV charging networks, ensuring that they meet the growing demands of Thailand’s evolving electric mobility landscape.
- 6 October 2024
- Published by MDPI AG in World Electric Vehicle Journal
- Vol. 15 (10) , 453
Open AccessAdaptive Multi-Agent Reinforcement Learning for Optimizing Dynamic Electric Vehicle Charging Networks in Thailand
The rapid growth of electric vehicles (EVs) necessitates efficient management of dynamic EV charging networks to optimize resource utilization and enhance service reliability. This paper explores the application of adaptive multi-agent reinforcement learning (MARL) to address the complexities of EV charging infrastructure in Thailand. By employing MARL, multiple autonomous agents learn to optimize charging strategies based on real-time data by adapting to fluctuating demand and varying electricity prices. Building upon previous research that applied MARL to static network configurations, this study extends the application to dynamic and real-world scenarios, integrating real-time data to refine agent learning processes and also evaluating the effectiveness of adaptive MARL in maximizing rewards and improving operational efficiency compared to traditional methods. Experimental results indicate that MARL-based strategies increased efficiency by 20% and reduced energy costs by 15% relative to conventional algorithms. Key findings demonstrate the potential of extending MARL in transforming EV charging network management, highlighting its benefits for stakeholders, including EV owners, operators, and utility providers. This research contributes insights into advancing electric mobility and energy management in Thailand through innovative AI-driven approaches. The implications of this study include significant improvements in the reliability and cost-effectiveness of EV charging networks, fostering greater adoption of electric vehicles and supporting sustainable energy initiatives. Future research directions include enhancing MARL adaptability and scalability as well as integrating predictive analytics for proactive network optimization and sustainability. These advancements promise to further refine the efficacy of EV charging networks, ensuring that they meet the growing demands of Thailand’s evolving electric mobility landscape.
- Open Access
- 26 October 2023
- Published by Silpakorn University in Science, Engineering and Health Studies
- p. 23040003
Reforming time measurement of hydrophobic and hydrophilic insulator surface via centroid tracking
Flashover between insulator surfaces is the most serious issue impacting power system stability related to power failures. It is caused by insulator surface degradation, which causes a flashover loss in insulation efficiency due to a change in the hydrophobicity class (HC) described in IEC TS 62073. The surface tension method is one of the measurement techniques used in this study. This study aimed to research an algorithm for transitioning from conventional measurement methods to a suggested approach for classifying surface tension based on the reforming time that applies to the centroid tracking technique. This research provides manual input for the automated image processing method. The main method is centroid tracking segmentation in a wet area (CTSWA). The comparative timing between adjacent manual frames was examined, yielding results known as ground truth (GT), and our approach (CTSWA) was demonstrated. Most results had a reforming time variance of less than 3% compared to GT. The use of the studied method yields three benefits, including automatic reforming time verification, which can produce acceptable results from more sensitive and reliable insulator inspections. It can also be applied to preventive maintenance planning (PM). Additionally, it reduces the limitations of human decision-making.
- 26 October 2023
- Published by Silpakorn University in Science, Engineering and Health Studies
- p. 23040003
Open AccessReforming time measurement of hydrophobic and hydrophilic insulator surface via centroid tracking
Flashover between insulator surfaces is the most serious issue impacting power system stability related to power failures. It is caused by insulator surface degradation, which causes a flashover loss in insulation efficiency due to a change in the hydrophobicity class (HC) described in IEC TS 62073. The surface tension method is one of the measurement techniques used in this study. This study aimed to research an algorithm for transitioning from conventional measurement methods to a suggested approach for classifying surface tension based on the reforming time that applies to the centroid tracking technique. This research provides manual input for the automated image processing method. The main method is centroid tracking segmentation in a wet area (CTSWA). The comparative timing between adjacent manual frames was examined, yielding results known as ground truth (GT), and our approach (CTSWA) was demonstrated. Most results had a reforming time variance of less than 3% compared to GT. The use of the studied method yields three benefits, including automatic reforming time verification, which can produce acceptable results from more sensitive and reliable insulator inspections. It can also be applied to preventive maintenance planning (PM). Additionally, it reduces the limitations of human decision-making.