• รางวัลทางวิชาการระดับนานาชาติและระดับชาติ
  • รางวัลการนำเสนอดีเด่นจากการนำเสนอผลงานวิจัยในที่ประชุมวิชาการระดับนานาชาติ The 20th International Conference on Food Science and Nutrition, August 27-28, 2018, Paris, France.
  • รางวัลการนำเสนอดีเด่นจากการนำเสนอผลงานวิจัยในที่ประชุมวิชาการระดับนานาชาติ The VIII International Scientific Conference “Modern trends in science and technology”, Association of Korean Cultural Centers of the Republic of Uzbekistan & STS “Tinbo”, November 18, 2016, Tashkent, Uzbekistan.
  • รางวัล Best Poster Award จากการประชุมวิชาการวิศวกรรมอาหารแห่งชาติ ครั้งที่ 7 (The 7^th National Food Engineering Conference; FENETT 2021) สถาบันเทคโนโลยีพระจอมเกล้าเจ้าคุณทหารลาดกระบัง
  • โล่ประกาศเกียรติคุณของมหาวิทยาลัยเกษตรศาสตร์ ประจำปี 2563 จากผลงานการตีพิมพ์และอ้างอิงสูงสุดใน TOP 2% ของโลก สาขา Food Science จาก World’s Top 2% Scientists by Stanford University
  • รางวัลบุคลากรดีเด่นด้านการวิจัยและนวัตกรรม ด้านการวิจัย สายวิทยาศาสตร์ ประจำปี 2562 มหาวิทยาลัยเกษตรศาสตร์
  • รางวัลนักวิจัยผู้สร้างสรรค์ผลงานวิจัยตีพิมพ์ระดับนานาชาติ ต่อเนื่องเป็นประจำทุกปี ตั้งแต่ประจำปี 2550-2561 มหาวิทยาลัยเกษตรศาสตร์
  • ได้รับคัดเลือกในการเข้าร่วมโครงการ The “Innovative and Sustainable Competitiveness in Food & Drink Technology” programme in the UK, funded by The Newton UK-Thailand Research and Innovation Partnership Fund, March 1-7, 2015, United Kingdom. จาก British Council, สกว. และ Newton Fund
  • ทุนวิจัยหลังปริญญาเอก ประจำปี 2549 (Post-doctoral fellowship 2006) จาก Korea Science & Engineering Foundation
  • บุคลากรสายวิชาการและนักวิจัยดีเด่นของมหาวิทยาลัยเกษตรศาสตร์ ประจำปี 2560 ด้านการวิจัย สายวิทยาศาสตร์ กลุ่มอายุตั้งแต่ 40 ปีขึ้นไป
  • ผู้สร้างชื่อเสียงให้คณะฯ ด้านนวัตกรรมและการแข่งขัน ประจำปีการศึกษา 2558 คณะวิศวกรรมศาสตร์ กำแพงแสน
  • อาจารย์ดีเด่นด้านงานวิจัย คณะวิศวกรรมศาสตร์ กำแพงแสน ประจำปี 2556
  • รางวัลอาจารย์ดีเด่น ด้านวิจัย มหาวิทยาลัยเกษตรศาสตร์ วิทยาเขตกำแพงแสน ประจำปี 2553
  • รางวัลนักวิจัย คณะวิศวกรรมศาสตร์ กำแพงแสน ประจำปี 2553

• วิทยากรของสมาคมสมองกลฝังตัวไทย
• กรรมการฝ่าย Tutorial ของการประชุมวิชาการ IEEE IECON’05, Raleigh, NC, USA
• ที่ปรึกษา บริษัท อีรูไดท์ เอ็นจิเนียริ่ง จำกัด (Automation business) ปี 2561-2564
• ที่ปรึกษา บริษัท ฟินิซิส จำกัด (AI and machine learning system) ปี 2562-2564
• วิทยากรด้าน Data Science และ Data Engineering ของ DEPA, Thailand.
• ที่ปรึกษาด้านระบบจัดการฐานข้อมูลของกรมพัฒนาที่ดิน ปี 2549-2550
• ที่ปรึกษาโครงการติดตั้งระบบเตือนภัยล่วงหน้า (early warning) สำหรับพื้นที่เสี่ยงอุทกภัย–ดินถล่มในพื้นที่ลาดชัน   และพื้นที่ราบเชิงเขา ปีงบประมาณ 2551-2563 กรมทรัพยากรน้ำ
• กรรมการสาขาคอมพิวเตอร์ โครงการพัฒนาอัจฉริยภาพทางวิทยาศาสตร์และเทคโนโลยีสำหรับเด็กและเยาวชน สำนักงานพัฒนาวิทยาศาสตร์และเทคโนโลยีแห่งชาติ 2546-2553
• วิทยากรค่ายคัดเลือกคอมพิวเตอร์โอลิมปิก ปี 2550
• อาจารย์ที่ปรึกษา ทีม Zeabus AUV (Autonomous Underwater Vehicle) ได้รับรางวัลที่ 5 จาก 48 ทีม                  จาก Association for Unmanned Vehicle Systems International (AUVSI) ในการแข่งขัน Robosub 2016         ณ เมือง San Diego, CA, USA.
• อาจารย์ที่ปรึกษา ทีม SKUBA ทีมหุ่นยนต์เตะฟุตบอล Robocup ของมหาวิทยาลัยเกษตรศาสตร์ ได้รับรางวัลชนะเลิศระดับโลก 3 ปี ปี 2552, 2553, 2554, 2555

• Journal Publications (International)

  1. Kasetkasem, Y. Tipsuwan, S. Tulsook, A. Muangkasem, A. Leangaramkul and P. Hoonsuwan, “A Pipeline Extraction Algorithm for Forward-Looking Sonar Images Using the Self-Organizing Map,” in IEEE Journal of Oceanic Engineering, doi: 10.1109/JOE.2020.2978989.
  2. Tipsuwan, S. Kamonsantiroj, J. Srisabye, and P. Chongstitvattana, “An auction-based dynamic bandwidth allocation with sensitivity in a wireless networked control system,” Computer & Industrial Engineering, Vol. 57, No. 1, pp. 114-124, 2009.
  3. Lertworasirikul and Y. Tipsuwan, “Moisture content and water activity prediction of semi-finished cassava crackers from drying process with artificial neural network,” Journal of Food Engineering, Vol. 84, pp. 65-74, 2008.
  4. Tipsuwan, “Discussion on: Robust H∞ Control of Networked Control Systems with Parameter Uncertainty and State-delay,” European Journal of Control, Vol. 12, no. 5, pp. 481-482, 2006.
  5. Tipsuwan and M.-Y. Chow, “Gain scheduler middleware: a methodology to enable existing controllers for networked control and teleoperation-part II: teleoperation,” IEEE Transactions on Industrial Electronics, vol. 51, no. 6, pp. 1228-1237, 2004. (impact factor 0.739)
  6. Tipsuwan and M.-Y. Chow, “Gain scheduler middleware: a methodology to enable existing controllers for networked control and teleoperation-part I: networked control,” IEEE Transactions on Industrial Electronics, vol. 51, no. 6, pp. 1218-1227, 2004. (impact factor 0.739)
  7. Tipsuwan and M.-Y. Chow, “On the gain scheduling for networked PI controller over IP network,” IEEE Transactions on Mechatronics, vol. 9, no. 3, pp. 491-498, 2004. (impact factor 0.954)
  8. -Y. Chow and Y. Tipsuwan, “Gain adaptation of networked DC motor controllers based on QoS variations,” IEEE Transactions on Industrial Electronics, vol. 50, no. 5, pp. 936–943, 2003. (impact factor 0.739)
  9. Tipsuwan and M.-Y. Chow, “Control methodologies in networked control systems,” Control Engineering Practice, vol. 11, no. 10, pp. 1099-1111, 2003. (impact factor 0.531)
  10. Li, M.-Y. Chow, Y. Tipsuwan, and J. C. Hung, “Neural-network-based motor rolling bearing fault diagnosis,” IEEE Transactions on Industrial Electronics, vol. 47, no. 5, pp. 1060-1069, 2000. (impact factor 0.739)

  Journal Publications (Domestic)

  1. Tipsuwan and M.-Y. Chow, “Analysis and Training of Compensation Neural Model for System Dynamics Modeling,” Journal of Research in Engineering and Technology, vol. 2, no. 1, pp. 28-43, 2005.

   

  • ผลงานวิชาการอื่น ๆ (เช่น Proceeding ตำรา ฯลฯ)

  Conferences (International)

  1. Leangaramkul, T. Kasetkasem, Y. Tipsuwan, T. Isshiki, T. Chanwimaluang, and P. Hoonsuwan, “Pipeline Segmentation Using Level-Set Method,” IEEE IGARSS 2019, Jul. 28 – Aug. 2, Yokohama, Japan.
  2. Leangaramkul, T. Kasetkasem, Y. Tipsuwan, T. Isshiki, T. Chanwimaluang, and P. Hoonsuwan, “Pipeline Direction Extraction Algorithm Using Level Set Method,” ECTI-CON 2019, pg. 634-637, Jul. 10- Jul. 13, Pattaya, Chonburi, Thailand.
  3. Prasatthong, T. Kasetkasem, Y. Tipsuwan, T. Isshiki, T. Chanwimaluang, and P. Hoonsuwan, “An Elevation Mapping Algorithm Based on a Markov Random Field Model for Underwater Exploration,” ECTI-CON 2019, pg. 638-641, Jul. 10- Jul. 13, Pattaya, Chonburi, Thailand.
  4. Tipsuwan, T. Kasetkasem, and S. Tulsook, “A Real-Time Pipeline Tracking Using a Forward-Looking Sonar,” International Petroleum Technology Conference (IPTC) 2019, Beijing, China, Mar. 26 – Mar. 28, 2019.
  5. Tulsook, T. Kasetkasem, Y. Tipsuwan, and Nobuhiko Sugino, “A pipeline extraction on forward-looking sonar images using the self-organizing map,” ECTI-CON 2018, Chiang Rai, Thailand, Jul. 18 – Jul. 21, 2018.
  6. Rattanawaorahirunkul. P. Sanposh, K. Sukvichai, Y. Tipsuwan, and P. Hoonsuwan, “Feedback Linearization with PID Controller Design for Autonomous Underwater Vehicle Using Particle Swarm Optimization (PSO),” ITC-CSCC 2017, Jul. 2 – Jul. 5, Busan, Korea,
  7. Kasetkasem, D. Worasawate, Y. Tipsuwan, P. Thiennviboon, and P. Hoonsuwan, “A pinger localization algorithm using sparse representation for autonomous underwater vehicles,” ECTI-CON 2017, Phuket, Thailand, Jun. 27 – Jun. 30, 2017.
  8. Hoonsuwan, Y. Tipsuwan, T. Slanvepan, “Development of a Novel Hybrid AUV System for Pipeline Inspection in Gulf of Thailand,” Offshore Technology Conference Asia 2016, Kuala Lumpur, Malaysia, Mar. 22 – Mar. 25, 2016.
  9. Hoonsuwan, T. Slanvetpan, and Y. Tipsuwan, “Development of a Novel Hybrid AUV System for Pipeline Inspection in Gulf of Thailand,” SETA conference 2016, Bangkok, Thailand, Mar. 23 – Mar. 25, 2016, pg. 1-5.
  10. Tipsuwan and P. Hoonsuwan, “Design and Implementation of an AUV for Petroleum Pipeline Inspection,” ICITEE’15, Chiang Mai, Thailand, Oct. 29 – Oct. 30, 2015, pg. 382-387.
  11. Parkpien and Y. Tipsuwan, “Time-Varying Periodic Disturbance Rejection in Peristaltic Pump Using Modified Repetitive Controller,” in ITC-CSCC’10, Pattaya, Thailand, 2010.
  12. Y. Tipsuwan, J. Srisabye, and S. Kamonsantiroj, “An experimental study of network-based DC motor speed control,” in IEEE IECON’07, Taipei, Taiwan, 2007.
  13. Wesnarat and Y. Tipsuwan, “A power efficient algorithm for data gathering from wireless water meter networks,” in IEEE INDIN’06, Singapore, 2006.
  14. Tipsuwan and S. Aiemchareon, “A Neuro-Fuzzy Network-Based Controller for DC Motor Speed Control,” in IEEE IECON’05, Raleigh, NC, Nov. 6 – Nov. 10, 2005.
  15. Tipsuwan and M.-Y. Chow, “An implementation of a networked PI controller over IP Network,” in IEEE IECON’03, Roanoke, VA, Nov. 2 – Nov. 6, 2003.
  16. Tipsuwan and M.-Y. Chow, “Neural network middleware for model predictive path tracking of networked mobile robot over IP network,” in IEEE IECON’03, Roanoke, VA, Nov. 2 – Nov. 6, 2003.
  17. Tipsuwan and M.-Y. Chow, “On the gain scheduling for networked PI controller over IP Network,” in IEEE/ASME AIM’03, Kobe, Japan, Jul. 20-24, 2003, pp. 640-645.
  18. Vanijjirattikhan, B. Ayhan, Y. Tipsuwan, and M.-Y. Chow, “A web-based distributed dynamics simulation of a three-phase induction motor,” in Proceedings of NSF Workshop on Teaching of First Courses on Power Electronics and Electric Drives and Advance Course on Power System Applications of Power Electronics, Tempe, Arizona, Jan. 5-7, 2003.
  19. Tipsuwan and M.-Y. Chow, “Gain adaptation of networked mobile robot to compensate QoS deterioration,” in IEEE IECON’02, Sevilla, Spain, Nov. 5-8, 2002, pp. 3146-3151.
  20. B. Almutairi, M.-Y. Chow, and Y. Tipsuwan, “Network-based controlled DC motor with fuzzy compensation,” in IEEE IECON’01, Denver, CO, Nov. 29 – Dec. 2, 2001, pp. 1844-1849.
  21. Tipsuwan and M.-Y. Chow, “Network-based controller adaptation based on QoS negotiation and deterioration,” in IEEE IECON’01, Denver, CO, Nov. 29 – Dec. 2, 2001, pp. 1794-1799.
  22. -Y. Chow and Y. Tipsuwan, “Network-based control systems: a tutorial,” in IEEE IECON’01, Denver, CO, Nov. 29 – Dec. 2, 2001, pp. 1593-1602.
  23. -Y. Chow and Y. Tipsuwan, “Neural plug-in motor coil thermal modeling,” in IEEE IECON’00, Nagoya, Japan, Oct. 22-28, 2000, pp. 1586-1591.
  24. Tipsuwan and M.-Y. Chow, “Analysis of training neural compensation model for system dynamics modeling,” in IEEE/INNS IJCNN’01, Washington, DC, Jul. 15-19, 2001, pp. 1250-1255.
  25. Tipsuwan and M.-Y. Chow, “Fuzzy logic microcontroller implementation for DC motor speed control,” in IEEE IECON’99, San Jose, CA, Nov. 29 – Dec. 3, 1999, pp. 1271-1276.
  26. -Y. Chow and Y. Tipsuwan, “Network-based control adaptation for network QoS variation,” in IEEE MILCOM’01, Vienna, VA, Oct. 28-31, 2001, pp. 257-261.

   

  Conferences (Domestic)

  1. รพีพงศ์ รัตนวรหิรัญกุล, พีระยศ แสนโภชน์, กาญจนพันธ์ สุขวิชชัย, ชนินทร์ ปัญจพรผล, ยอดเยี่ยม ทิพย์สุวรรณ์ และสุรเทพ นิลนนท์, “การแปลงระบบให้เป็นเชิงเส้นด้วยการป้อนกลับร่วมกับตัวควบคุมพีไอดี กรณีศึกษา: การควบคุมหุ่นยนต์ใต้น้ำอัตโนมัติ และการควบคุมพีเอช,” The Conference of TRS on Robotics and Industrial Technology 2017 (CRIT 2017), Bangkok, Thailand, Jun. 22, 2017.
  2. เอกลักษณ์ เวศนารัตน์ และยอดเยี่ยม ทิพย์สุวรรณ์, “วิธีการเก็บข้อมูลจากมิเตอร์น้ำประปาด้วยระบบเครือข่ายเซ็นเซอร์ไร้สาย” in International Conference on Embedded Systems and Intelligent Technology (ICESIT 2008), Bangkok, Thailand, Feb. 27-29, 2008.
  3. Aiemchareon, S. Lertworasirikul, and Y. Tipsuwan, “Fuzzy logic for sensory evaluation of tastes,” in Proceedings of the 6^th Agro-Industrial Conference, Bangkok, Thailand, May 28 – 29, 2004.

   

  Tutorial (International)

  1. -Y. Chow and Y. Tipsuwan, “Network-based control systems: a tutorial,” in IEEE IECON’01, Denver, CO, 29 Nov. – 2 Dec., 2001.

Almutairi, N. B., et al. (2001). Network-based controlled DC motor with fuzzy compensation.

This paper introduces a fuzzy logic compensation approach for the network-based controlled DC motor. The approach is based on modulating the control signal provided by the central controller in the network-based system with a single parameter. The inputs to the fuzzy compensator are the error signal between the reference and the actual output of the DC motor, and the output signal from the PI controller. The output from the fuzzy compensator is the modulator parameter. This parameter will modulate the output of the PI controller in order to reduce the effect of the network delays and different available bandwidth. The results show that using fuzzy compensation can be an effective approach to improve the performance of the DC motor controlled through the network.

Chow, M. Y. and Y. Tipsuwan (2000). Neural plug-in motor coil thermal modeling. IECON Proceedings (Industrial Electronics Conference), IEEE Computer Society.

With the latest advancement in technologies, many motor controls and protections now rely on the use of on-line motor data fed through embedded motor models (including thermal models) stored in microprocessors where the critical decisions are made. The accuracy of these embedded motor models has a direct effect on the performance and reliability of the motors. In this paper, we propose to use an Artificial Neural Network plug-in modeling concept to significantly increase the accuracy of the lumped-parameter motor thermal modeling approach. The neural plug-in approach could preserve the fast calculation response of the lumped-parameter model, preserve the physical meaning of thermal parameters, and increase the overall accuracy of the thermal model. This paper discusses and compares the motor thermal dynamics and its estimates by the three different models, lumped-parameter model, conventional neural network model, and neural plug-in model. The preliminary modeling results clearly indicate that the neural plug-in modeling approach is superior than either the lumpedparameter approach or the neural network approach. © 2000 IEEE.

Chow, M. Y. and Y. Tipsuwan (2001). Network-based control adaptation for network QoS variation.

Networks and their applications have been evolving substantially in the last two decades. A new and promising use of networks is in the area of high performance control and automation, which is developing into attractive and widespread military applications such as autonomous unmanned vehicles and telerobotics. Some of the major concerns in using networks to perform remote network-based control are QoS issues such as time delay and bandwidth constraints. Disturbances and unanticipated events often happen to network-based applications. When anomalies happen, if the network cannot provide the required QoS, the application may have to lower its performance requirement and use the assigned QoS to do the best as it can to maintain the application availability. This paper proposes the use of real-time application gain adaptation to compensate for QoS variations and deterioration. A network-based controlled Dc motor, which is often used in military vehicles for actuation and propulsion systems, is used in this paper to illustrate the effectiveness of the proposed scheme. In addition, this proactive use of application adaptability provides an extra degree of freedom for network QoS negotiation, protocol design and implementation.

Chow, M. Y. and Y. Tipsuwan (2001). Network-based control systems: A tutorial.

An overview is given on network-based control and recent network-based control techniques for handling the network delays. The techniques are based on various concepts such as state augmentation, queueing and probability theory, nonlinear control and perturbation theory, and scheduling. A general structure of a network-based control system, delay types, and delay behaviors are also described. Furthermore, the advantages and disadvantages of these techniques are highlighted.

Chow, M. Y. and Y. Tipsuwan (2002). Time sensitive network-based control systems.

Fundamental details of network-based control and recent network-based control techniques for handling network delays are presented. The techniques are based on various concepts such as state augmentation, queuing and probability theory, nonlinear control and perturbation theory, and scheduling. A general structure of a network-based control system, delay types, and delay behaviors are also described.

Chow, M. Y. and Y. Tipsuwan (2003). “Gain adaptation of networked DC motor controllers based on QOS variations.” IEEE Transactions on Industrial Electronics 50(5): 936-943.

Connecting a complex control system with various sensors, actuators, and controllers as a networked control system by a shared data network can effectively reduce complicated wiring connections. This system is also easy to install and maintain. The recent trend is to use networked control systems for time-sensitive applications, such as remote dc motor actuation control. The performance of a networked control system can be improved if the network can guarantee Quality-of-Service (QoS). Due to time-varying network traffic demands and disturbances, QoS requirements provided by a network may change. In this case, a network has to reallocate its resources and may not be able to provide QoS requirements to a networked control application as needed. Therefore, the application may have to gracefully degrade its performance and perform the task as best as possible with the provided network QoS. This paper proposes a novel approach for networked dc motor control systems using controller gain adaptation to compensate for the changes in QoS requirements. Numerical and experimental simulations, and prototyping, are presented to demonstrate the feasibility of the proposed adaptation scheme to handle network QoS variation in a control loop. The effective results show the promising future of the use of gain adaptation in networked control applications.

Hoonsuwan, P., et al. (2016). Development of a novel hybrid auv system for pipeline inspection in gulf of Thailand, Offshore Technology Conference.

Oil and gas companies are increasingly being forced to conduct their sub-sea pipeline inspections in increasingly more hostile and deeper waters. Typically, Remotely Operated Vehicles (ROV) are used for sub-sea pipeline inspections and these are controlled by experienced ROV operators from a surface support vessel, which tend to make ROV operations costly. Conversely, an Autonomous Underwater Vehicle (AUV) can perform sub-sea pipeline inspections without the need for a human operator. This paper sets-out to describe the development of a novel Hybrid AUV (HAUV) system, composed of two unmanned vehicles and designed specifically for sub-sea pipeline inspection. The first vehicle is a compact Unmanned Surface Vehicle (USV), which tracks a sub-sea pipeline from the sea surface. The second vehicle is a HAUV, which is connected to the USV via a fibre optic tether. Both vehicles operate together to automatically inspect sub-sea pipelines. The complete system is controlled by a remote control station on the surface. At this early stage of development, its capability is limited due to its size and battery power source but lab-scale units have been developed and have undergone field testing. Our team study is ongoing and endeavours to refine the HAUV system-capabilities enabling us to offer a cost-effective approach for sub-sea pipeline inspection in the near future. © 2016, Offshore Technology Conference

Kasetkasem, T., et al. (2021). “A Pipeline Extraction Algorithm for Forward-Looking Sonar Images Using the Self-Organizing Map.” IEEE Journal of Oceanic Engineering 46(1): 206-220.

An autonomous underwater vehicle (AUV) can operate automatically with a small number of humans and requires few resources when compared to a remotely operated vehicle (ROV). The pipeline inspection with the use of an AUV can be significantly cheaper than those of an ROV. Successful deployment of AUVs relies on accurate pipeline detection and extraction that can automatically locate and track a pipeline direction in real time. We proposed to use forward-looking sonar images to locate and extract pipeline paths since sonar can easily image through turbulence and small particles, commonly found in underwater environments. However, sonar images are prone to disturbance from the environment. Thus, as a superior alternative, we developed a pipeline detection algorithm by considering that a pipeline has a piecewise linear shape. Next, the self-organizing map (SOM) is employed to join the labeled segments together to form a pipeline track to extract the pipeline path for the navigation of an AUV since SOM can map a 2-D image of pipeline into a 1-D line. In our experiment, data obtained from the Gulf of Thailand are used for the performance analysis, and we are able to extract and describe a pipeline direction with accuracies between 90% and 97%. © 1976-2012 IEEE.

Kasetkasem, T., et al. (2017). A pinger localization algorithm using sparse representation for autonomous underwater vehicles, Institute of Electrical and Electronics Engineers Inc.

The problem of underwater Finger localization is a crucial part of the underwater pipeline monitoring and maintenance by using an AUV in oil and gas industries. In this problem, a Finger repeatedly transmits pulses of audio signals to an array of hydrophones. Due to the delay pattern, the direction of a Finger relative to the hydrophone array can be estimated. However, since underwater environment is multipath in nature, multiple copies of Finger pulses arrive at the hydrophones. In this paper, we employed the sparse representation to find the best combinations of the multipath signals, and use the direction of the first arrival path to be the direction of a Finger. © 2017 IEEE.

Leangaramkul, A., et al. (2019). Pipeline direction extraction algorithm using level set method, Institute of Electrical and Electronics Engineers Inc.

Autonomous underwater vehicles (AUVs), unmanned underwater vehicles, provide lower operation costs in underwater pipeline inspection than remotely operated vehicles (ROVs), since there is no need for a human operator. However, the navigation algorithm is an important part of the successful deployment of AUVs. In this work, we propose an algorithm that extracts the direction of a pipeline based on the level set method (LSM). This direction shall be used for the automatic navigation of an AUV. The low light and turbid water prohibit the use of an optical camera. Instead, a forward-looking sonar (FLS) was selected to provide input sequence images. Due to speckle noise, the traditional image segmentation algorithm cannot be used. Thus, the LSM is applied to represent the direction of pipelines. Lastly, the post-processing which estimates the direction is used to increase the accuracy. From experiments, our algorithm can extract the pipeline direction with accuracies of as high as 94.33%. © 2019 IEEE.

Leangaramkul, A., et al. (2019). Pipeline Segmentation using Level-Set Method, Institute of Electrical and Electronics Engineers Inc.

Autonomous underwater vehicles (AUVs), unmanned underwater vehicles, are cheaper to operate than remotely operated vehicles (ROVs), since an AUV does not require a trained human operator to control. As a result, in this paper, we propose the pipeline tracking algorithm using sequences of the forward-looking sonar (FLS) images installed on a preprogram AUV. The FLS is more suitable to be used in the subsurface environment than an optical camera due to the limited visibility and floating particles in the sub-sea surface environment. In our work we first employed the speckle noise reduction to the FLS images. Then, we applied the level-set method (LSM) to extract a pipeline boundary in each frame. Lastly, the post-processing step was designed to link the unconnected segments together to from a complete pipeline. Our algorithm can perform the segmentation and tracking with more than 85% accuracy. © 2019 IEEE.

Lertworasirikul, S. and Y. Tipsuwan (2008). “Moisture content and water activity prediction of semi-finished cassava crackers from drying process with artificial neural network.” Journal of Food Engineering 84(1): 65-74.

This paper is concerned with a prediction of moisture content and water activity of semi-finished cassava crackers from a hot air drying process in a tray dryer. A Multilayer Feedforward Neural Network in the form of Nonlinear-Auto-Regressive with Exogenous input (MFNN-NARX) was proposed to predict the product quality from the dynamic drying process. The process was carried out at seven drying temperature settings of 50, 55, 60, 65, 70, 75, and 80 °C. The MFNN-NARX was composed of one hidden layer, three exogenous inputs (drying temperature, relative humidity, and sample temperature), and two state inputs and outputs (moisture content and water activity). A number of hidden neurons and transfer functions were investigated in this study. Based on our results, the best network was composed of nine hidden nodes and used a logarithmic sigmoid transfer function in the first layer. The mean squared error (MSE) and regression coefficient (r2) between the normalized predicted and experimental outputs from the best network were 0.0034 and 0.9910, respectively. A simulation test with a testing data set showed that MSE was low and r2 was close to 1. This result showed the good generalization of the developed model. © 2007 Elsevier Ltd. All rights reserved.

Li, B., et al. (2000). “Neural-network-based motor rolling bearing fault diagnosis.” IEEE Transactions on Industrial Electronics 47(5): 1060-1069.

Motor systems are very important in modern society. They convert almost 60% of the electricity produced in the U.S. into other forms of energy to provide power to other equipment. In the performance of all motor systems, bearings play an important role. Many problems arising in motor operations are linked to bearing faults. In many cases, the accuracy of the instruments and devices used to monitor and control the motor system is highly dependent on the dynamic performance of the motor bearings. Thus, fault diagnosis of a motor system is inseparably related to the diagnosis of the bearing assembly. In this paper, bearing vibration frequency features are discussed for motor bearing fault diagnosis. This paper then presents an approach for motor rolling bearing fault diagnosis using neural networks and time/frequency-domain bearing vibration analysis. Vibration simulation is used to assist in the design of various motor rolling bearing fault diagnosis strategies. Both simulation and real-world testing results obtained indicate that neural networks can be effective agents in the diagnosis of various motor bearing faults through the measurement and interpretation of motor bearing vibration signatures.

Prasatthong, N., et al. (2019). An elevation mapping algorithm based on a markov random field model for underwater exploration, Institute of Electrical and Electronics Engineers Inc.

The 2-D Forward-looking Sonar (2D-FLS) is a new technology of sonar signals that increases the performance of underwater exploration of an Autonomous Underwater Vehicle (AUV). Because the AUV is a fully automatic robot that can handle various missions and does not require humans to control its operation, FLS is the best tool for underwater navigation in poor visibility conditions. In this paper, we used an FLS image sequence to estimate the height of the pipeline and create an elevation map containing information about the height in each of the pixels. In our algorithm, we employed the Markov random field to model the elevation map, since elevations of neighboring pixels are more likely to have similar values. Next, the Metropolis Algorithm (MA) is used to find the solution of the maximum a posterori equation. © 2019 IEEE.

Siriyakorn, V., et al. (2019). Development of ZEABUS 2018 AUV, Institute of Electrical and Electronics Engineers Inc.

Zeabus 2018, an Autonomous Underwater Vehicle (AUV), has developed by undergraduate students from various departments in the Faculty of Engineering at Kasetsart University in order to join the RoboSub competition since 2014. The aims of developing the AUV are to efficiently control in all 6 degree-of-freedom, to accurately detect underwater objects, and to have quick and easy adaptation for various of competition tasks. Currently, the AUV has completed many tasks in the competition; however, there are several issues that require improvements. In the 2018 model, the AUV is maneuvered with 8 thrusters mounted at conscientious positions together with various sensors for navigation and control. Data are collected from these sensors and processed by two small-size computers inside the AUV. There are power and communication systems that were developed carefully so that the AUV can be operated accurately. Moreover, a software system was implemented thoroughly to control the AUV and to detect underwater objects. These elaborations make the Zeabus 2018 having higher efficiency and performance than the previous models. © 2019 IEEE.

Tipsuwam, Y. and M. Y. Chow (2004). Model predictive path tracking via middleware for networked mobile robot over IP network.

The potential use of IP networks for real-time high performance robots and automation is enormous and appealing. A widely attractive objective for an IP-based mobile robot is to control a mobile robot over the IP network to track a predefined path. This paper proposes a model predictive path tracking control methodology over an IP network via middleware. In addition to the normal use of middleware, this paper utilizes middleware to schedule a control parameter for IP network delay compensation. The parameter is adjusted externally at the output of the path tracking algorithm with respect to the current network traffic conditions and a predictive performance measure computed by a neural network. Simulation results show that the mobile robot with neural network middleware provides significantly better IP networked control system performance.

Tipsuwan, Y. (2006). “Discussion on: “Robust H∞ control of networked control systems with parameter uncertainty and State-delay”.” European Journal of Control 12(5): 481-482.

Tipsuwan, Y. and S. Aiemchareon (2005). A neuro-fuzzy network-based controller for DC motor speed control.

Network-based control (NBC) systems can provide several advantages among traditional control systems. Nevertheless, the performances of NBC systems can be degraded due to undesired network behaviors such as networkinduced delays. Several NBC algorithms usually neglect several network behaviors due to assumptions in problem formulations. The incompleteness and ambiguity of this network information implies ambiguities in NBC performances. In this paper, we propose a novel NBC gain scheduling scheme by applying a SANFIS (Self-Adaptive Neuro-Fuzzy Inference System) along with gain scheduling to handle ambiguities in network behaviors. The SANFIS is utilized to classify a current network condition in order to select an optimal gain for this condition. A simulation result shows that the PI controller with the proposed approach yields significantly better NBC performances. ©2005 IEEE.

Tipsuwan, Y. and M.-Y. Chow (1999). Fuzzy logic microcontroller implementation for DC motor speed control, Los Alamitos, CA, United States, IEEE.

This paper described an alternative method to implement a fuzzy logic speed controller for a DC motor using a fuzzy logic microcontroller. The design, implementation, and experimental results on load and no-load conditions are presented. The controller can be implemented by using only a small amount of components and easily improved to be an adaptive fuzzy controller. The controller also provides high performance with compact size and low cost.

Tipsuwan, Y. and M. Y. Chow (2001). Analysis of training neural compensation model for system dynamics modeling.

Incorporating a nominal model as a priori knowledge with a neural network to model a physical system has shown better performance than using only a conventional network model. However, there has been no explicit mathematical reason to describe why this technique called neural compensation modeling results in such improvement. The purpose of this paper is to analyze this concept by deriving a mathematical explanation of the neural compensation model compared to a convention network model. The explanation is derived based on normalization procedures of training sets and the properties of norms. In addition, the analysis is illustrated by using a motor coil thermal system.

Tipsuwan, Y. and M. Y. Chow (2001). Network-based controller adaptation based on QoS negotiation and deterioration.

Networks and their applications have been evolving substantially in the last two decades. A new and promising use of networks is in the area of high performance control and automation, which is developing into attractive and widespread applications. Some of the major concerns in using networks to perform remote network-based control are QoS issues such as time delay and bandwidth constraints. Disturbances and unanticipated events often happen to network-based applications. When anomalies happen, if the network cannot provide the required QoS, the application may have to lower its performance requirement and use the assigned QoS to do the best as it can to maintain the application availability. This paper proposes the use of real-time application gain adaptation to compensate for QoS variations and deterioration. A numerical and an experimental simulation of a network-based controlled DC motor are used in this paper to illustrate the effectiveness of the proposed scheme.

Tipsuwan, Y. and M. Y. Chow (2002). Gain adaptation of networked mobile robot to compensate QoS deterioration.

The performance of a robot operated over a data network does not only depend on a control algorithm used, but also on network conditions. Providing network QoS (Quality-of- Service) to a networked robot system could significantly improved its system performances. However, the network QoS can degrade due to several factors, such as congestion and interference, and can affect the overall system performances. We propose a gain adaptation approach to compensate deteriorative changes in network QoS in order to maintain the performances of a robot system as much as possible. The approach is demonstrated by path tracking control of networked differential drive mobile robot over a QoS enabled network. The simulation results show that when the gain adaptation is applied, the robot can effectively tolerate network QoS deterioration, and increase the overall system robustness. The concept of gain adaptation can be easily extended to other network-based control applications.

Tipsuwan, Y. and M. Y. Chow (2003). “Control methodologies in networked control systems.” Control Engineering Practice 11(10): 1099-1111.

The use of a data network in a control loop has gained increasing attentions in recent years due to its cost effective and flexible applications. One of the major challenges in this so-called networked control system (NCS) is the network-induced delay effect in the control loop. Network delays degrade the NCS control performance and destabilize the system. A significant emphasis has been on developing control methodologies to handle the network delay effect in NCS. This survey paper presents recent NCS control methodologies. The overview on NCS structures and description of network delays including characteristics and effects are also covered. © 2003 Published by Elsevier Ltd.

Tipsuwan, Y. and M. Y. Chow (2003). Neural Network Middleware for Model Predictive Path Tracking of Networked Mobile Robot over IP Network.

The potential use of IP networks for real-time high performance robots and automation is enormous and appealing. A widely attractive objective for an IP-based mobile robot is to control a mobile robot over the IP network to track a predefined path. This paper proposes a model predictive path tracking control methodology over an IP network via middleware. In addition to the normal use of middleware, this paper utilizes middleware to schedule a control parameter for IP network delay compensation. The parameter is adjusted externally at the output of the path tracking algorithm with respect to the current network traffic conditions and a predictive performance measure computed by a neural network. Simulation results show that the mobile robot with neural network middleware provides significantly better IP networked control system performance.

Tipsuwan, Y. and M. Y. Chow (2003). On the gain scheduling for networked PI controller over IP network, Institute of Electrical and Electronics Engineers Inc.

The potential use of networks for real time-time high performance control and automation is enormous and appealing. Replacing a widely used PI controller by a new networked controller for networked control capability can be costly and time-consuming. This paper proposes a methodology based on gain scheduling with respect to real-time IP traffic conditions to enhance the existing PI controller so it can be used over IP networks with a general network protocol like Ethernet. This paper first describes the gain scheduling approach based on constant network delays using a rational function approach. The formulation is extended to random IP network RTT (round trip time) delays by using the generalized exponential distribution model. Simulation results show that the PI controller with gain scheduling provides significantly better networked control system performance. © 2003 IEEE.

Tipsuwan, Y. and M. Y. Chow (2004). “Gain scheduler middleware: A methodology to enable existing controllers for networked control and teleoperation – Part I: Networked control.” IEEE Transactions on Industrial Electronics 51(6): 1218-1227.

Conventionally, in order to control an application over a data network, a specific networked control or teleoperation algorithm to compensate network delay effects is usually required for controller design. Therefore, an existing controller has to be redesigned or replaced by a newcontroller system. This replacement process is usually costly, inconvenient, and time consuming. In this paper, a novel methodology to enable existing controllers for networked control and teleoperation by middleware is introduced. The proposed methodology uses middleware to modify the output of an existing controller based on a gain scheduling algorithm with respect to the current network traffic conditions. Since the existing controller can still be utilized, this approach could save much time and investment cost. Two examples of the middleware applied for networked control and teleoperation with IP network delays are given in these two companion papers. Part I of these two companion papers introduces the concept of the proposed middleware approach. Formulation, delay modeling, and optimal gain finding based on a cost function for a case study on DC motor speed control with a proportional-integral (PI) controller are also described. Simulation results of the PI controller shows that, with the existence of IP network delays, the middleware can effectively maintain the networked control system performance and stabilize the system. Part II of this paper will cover the use of the proposed middleware concept for a mobile robot teleoperation. © 2004 IEEE.

Tipsuwan, Y. and M. Y. Chow (2004). “Gain scheduler middleware: A methodology to enable existing controllers for networked control and teleoperation – Part II: Teleoperation.” IEEE Transactions on Industrial Electronics 51(6): 1228-1237.

This paper is the second of two companion papers. The foundation for the external gain scheduling approach to enable an existing controller via middleware for networked control with a case study on a proportional-integral (PI) controller for dc motor speed control over IP networks was given in Part I. Part II extends the concepts and methods of the middleware called gain scheduler middleware (GSM) in Part I to enable an existing controller for mobile robot path-tracking teleoperation. By identifying network traffic conditions in real-time, the GSM will predict the future tracking performance. If the predicted tracking performance tends to be degraded over a certain tolerance due to network delays, the GSM will modify the path-tracking controller output with respect to the current traffic conditions. The path-tracking controller output is modified so that the robot will move with the fastest possible speed, while the tracking performance is maintained in a certain tolerance. Simulation and experimental results on a mobile robot path-tracking platform show that the GSM approach can significantly maintain the robot path-tracking performance with the existence of IP network delays. © 2004 IEEE.

Tipsuwan, Y. and M. Y. Chow (2004). Gain scheduling middleware for networked mobile robot control.

This paper proposes a novel control methodology for remote mobile robot control over a network via middleware. The controller output is adapted via middleware with respect to current network traffic conditions. The middleware can be implemented in a modular structure. Thus, a controller upgrade or modification for other types of network protocols or different control objectives can be achieved easily. A case study on a mobile robot path-tracking with IP network delays is described. The effectiveness of the proposed approach is verified by experimental results.

Tipsuwan, Y. and M. Y. Chow (2004). “On the gain scheduling for networked PI controller over IP network.” IEEE/ASME Transactions on Mechatronics 9(3): 491-498.

The potential use of networks for real-time high-performance control and automation is enormous and appealing. Replacing a widely used proportional-integral (PI) controller by a new networked controller for networked control capability can be costly and time-consuming. This paper proposes a methodology based on gain scheduling with respect to real-time IP traffic conditions to enhance the existing PI controller so it can be used over IP networks with a general network protocol like Ethernet. This paper first describes the gain scheduling approach based on constant network delays using a rational function approach. The formulation is extended to random IP network round-trip time (RTT) delays by using the generalized exponential distribution model. Simulation results show that the PI controller with gain scheduling provides significantly better networked control system performance. © 2004 IEEE.

Tipsuwan, Y., et al. (2003). An Implementation of a Networked PI Controller over IP Network.

This paper presents an implementation of a networked PI controller using a gain scheduling methodology with respect to real-time IP traffic conditions. The implementation enables the existing PI controller to be used over IP networks with a general network protocol like Ethernet. This paper first describes the controller design scheme using a generalized exponential distribution traffic model. The gain scheduling technique is also explained. The detail of networked PI controller implementation based on RTLinux on an actual DC motor setup is then described. Experimental results show that the proposed implementation is feasible to improve the performance of the PI controller operated over IP networks.

Tipsuwan, Y. and P. Hoonsuwan (2015). Design and implementation of an AUV for petroleum pipeline inspection, Institute of Electrical and Electronics Engineers Inc.

Inspection of petroleum pipelines is very crucial for oil and gas companies. Using a ROV (Remotely Operated Vehicle) for pipeline inspection requires extensive expenses due to heavy equipment and a large number of crew members for operations. In order to save the inspection cost, Kasetsart University and PTTEP have cooperated to conduct a research and development of a specialized AUV (Autonomous Underwater Vehicle). This paper describes a design and implementation of our lab-scale AUV. The AUV is controlled by using a 6-degree-of-freedom PID controller. Sensors used on the AUV include a sonar, a DVL, a pressure sensor, and an altimeter. A software structure of our AUV is based on ROS (Robot Operation System). © 2015 IEEE.

Tipsuwan, Y., et al. (2009). “An auction-based dynamic bandwidth allocation with sensitivity in a wireless networked control system.” Computers and Industrial Engineering 57(1): 114-124.

Applications of control systems on wireless networks have been widely utilized due to their mobility. However, the performances of these networked control systems (NCS) could be degraded and become unstable by network-induced delays. Existing dynamic bandwidth allocation methods for NCS assign bandwidth to each system with respect to different priorities in an ascending order. However, these NCS may not be given bandwidths at equilibrium such that each of these NCS is satisfied with respect to bandwidth requests of other NCS. Therefore, some NCS may always consume most of given bandwidths, while others may never be given satisfied bandwidths. This paper proposes a dynamic bandwidth allocation methodology that controls bandwidths given to open-loop NCS to be at Nash equilibrium. In this paper, the average sensitivities of NCS are used in utility functions in order to evaluate the effects of network-induced delays for NCS. Then, a control center or an access point will use the proposed methodology to allocate bandwidths for all NCS based on Nash equilibrium. Simulations and experiments were setup from a set of DC motors controlled over a wireless network. Simulation and experimental results show good performances of the proposed methodology compared with three other methods. © 2008 Elsevier Ltd. All rights reserved.

Tipsuwan, Y., et al. (2019). A real-time pipeline tracking using a forward-looking sonar, International Petroleum Technology Conference (IPTC).

The pipeline inspection is one of the most critical tasks in the oil and gas industries. The operation of a remotely operated vehicle (ROV) for the pipeline inspection is very costly since it requires both a human operator and the support vessel to which an ROV must be tethered. Furthermore, this tether also limits the surveillance ability of an ROV. Thus, the use of autonomous underwater vehicles (AUVs) can greatly reduce the operation cost of pipeline inspection since an AUV can freely and automatically navigate without tethering to support vessel. In order for an AUV to navigate automatically under the limited vision in the underwater environment, the forward-looking sonar (FLS) is the essential part since the quality of images captured by an optical camera degrade significantly by the turbid water and the low-light condition whereas images produced from an acoustic sonar As a result, in this work, we are interested in the use of a 2-D multi-beam Forward-Looking Sonar (FLS) to capture echo images on a frontal vision since acoustic signals can pass through tiny particles in turbid medium water [1]. This deployment ensures that an image of pipelines can be captured regardless of low underwater visibility conditions. Other types of sonars that are regularly used in underwater visual inspection include the side scan sonar (SSS), synthetic aperture sonar (SAS), and multi-beam echo sounder (MBES). There are a limited number of works that focus on the pipeline detection problem. An optical camera was employed in [2] for visual feedback and heading control, SSS and MBES were used in [3], [4] and [5] for pipeline tracking, and, in [6], FLS was used for linear object detection and tracking. © 2019, International Petroleum Technology Conference

Tipsuwan, Y. and S. Soucek (2005). “A message from the tutorial co-chairs.”  2005: 16-17.

Tipsuwan, Y., et al. (2007). An experimental study of network-based DC motor speed control using SANFIS.

Network-based control (NBC) systems can provide several advantages among traditional control systems. Nevertheless, the performances of NBC systems can be degraded due to undesired network behaviors such as network-induced delays. Several NBC algorithms usually neglect several network behaviors due to assumptions in problem formulations. The incompleteness and ambiguity of this network information implies ambiguities in NBC performances. In this paper, we applied a novel NBC gain scheduling scheme by applying a SANFIS (Self-Adaptive Neuro-Fuzzy Inference System) along with gain scheduling to handle ambiguities in network behaviors. The SANFIS is utilized to classify a current network condition in order to select an optimal gain for this condition. An experimental result shows that the PI controller with the proposed approach yields significantly better NBC performances. ©2007 IEEE.

Tulsook, S., et al. (2019). A pipeline extraction on forward-looking sonar images using the self-organizing map, Institute of Electrical and Electronics Engineers Inc.

The underwater pipeline surveillance and inspection using an autonomous underwater vehicle (AUV) is the future of the oil and gas industries since the inspection using a remotely operated underwater vehicle (ROV) is very expensive. However, the successful deployment of AUVs relies on the accurate pipeline path extraction that can automatically navigate along its direction in real-time. Due to the limited visibility of the underwater environment, we proposed to use the forward-looking sonar (FLS) to overcome environment dependencies. However, the sonar images are very noisy from a nature of acoustic imaging itself. Thus, this paper mainly contributes a real-time pipeline extraction to overcome speckle noise and intensity inhomogeneity in FLS by utilizing cell-averaging constant false alarm rate (CA-CFAR) and the self-organizing map (SOM). In our experiment, the pipeline images data obtained from the Gulf of Thailand were used for the performance analysis where our method can accurately extract more than 89% of the dataset. © 2018 IEEE

Vanijjirattikhan, R., et al. (2004). Feedback preprocessed unmanned ground vehicle network-based controller characterization.

This paper characterizes the performance of a Feedback Preprocessor (FP) that is used to alleviate the effect of the delay time on an Unmanned Ground Vehicle (UGV) path tracking problem in Network-Based Control (NBC) environment. The FP estimates the UGV state in order to compensate for the effect of a constant time delay induced by the network. The FP technique can be implemented as an external module appending to an existing nonlinear control system without having to redesign the controller. This technique uses the plant dynamics to estimate the future state of the plant under network-based control. The overall NBC system performance is investigated via simulation in terms of UGV system dynamics responses and network time delay magnitudes. The approach and result in this paper can be used to estimate the performance of any similar UGV operating in an NBC environment. An intermediate parameter, UGV response time, may be used to relate the result in this paper to other UGV in general. ©2004 IEEE.

Wesnarat, A. and Y. Tipsuwan (2006). A power efficient algorithm for data gathering from wireless water meter networks, IEEE Computer Society.

A traditional method to gather water consumption data from water meters in residential areas by using human recorders is costly and time consuming. Many AMR (Automatic Meter Reading) methods have been proposed to assist data gathering. A wireless ad-hoc sensor network configuration could be an alternative to reduce the cost of AMR. Some existing sensor network protocols such as LEACH, PEGASIS, and PEDAP could be applied. However, these protocols may not be perfectly suitable for water meters because data fusion is not possible in this particular application. In this paper, we propose a power efficient data gathering algorithm for wireless water meter networks. This algorithm uses a new approach to generate trees in order to distribute loads of root nodes to achieve a longer network lifetime. Simulation results show that our algorithm could yield better performances than a classical minimum spanning tree algorithm used in some existing algorithms such as PEDAP. ©2006 IEEE.