Norwegian version of this page

Ilya Tyapin

Associate Professor Department of Engineering Sciences

Email: ilya.tyapin@uia.no
Phone: +47 37 23 38 11
Office: D3024 (Jon Lilletuns vei 9, 4879 Grimstad, Norway)

Download business card

Areas of responsibility

University of Agder, July 2014 - present, Associate Professor.

University of Agder, Feb 2011 – July 2014, Postdoctor.

LULEÅ UNIVERSITY OF TECHNOLOGY, Feb 2010 – July 2011, Postdoctor.

UNIVERSITY OF QUEENSLAND, Oct 2004 – Dec 2009, Ph.D student.

Research

Academic interests

Research:

Mechatronics, Mechanics, Autonomous Systems, Motion Control, Robotics.

Teaching:

§ MAS 219 – Hydraulics.

§ MAS 219 – Drives.

§ MAS 216 – Industrial Robots.

§ MAS 407 – Modeling and Simulations.

§ MAS 105 – Product Development.

§ MAS 221 – Industrial IT and Robotics

§ MAS 410 – Hydraulics.

§ MAS 409 – Electric Drives.

Projects

Automated soRting and safE pre-procesSing of EoL BaTteries with nOvel smart and fast dismantling, and sepaRation technolgies for direct reuse of high purity materials in Energy storage application (RESTORE)

Research groups

Økter, Martin Bjaadal; Brekke, Vegard; Dybdahl, Eirik; Tyapin, Ilya & Choux, Martin Marie Hubert (2026). A Robotic Setup for Adaptive EV-Battery Disassembly Using ROS2 in a Near-Industrial Environment. IEEE International Conference on System of Systems Engineering (SoSE). ISSN 2835-3307. doi: 10.1109/SoSE69681.2026.11622357. Full text in Research Archive Show summary
The growing number of end-of-life electric vehicle (EV) batteries demands scalable and adaptive disassembly solutions to enable efficient recycling. This paper presents a near-industrial robotic demonstrator for adaptive EV battery pack disassembly. The system integrates two industrial manipulators, force/torque sensing, automatic tool changing, and structured-light 3D vision within a ROS2-based perception and control architecture. A YOLO-based detection pipeline combined with point-cloud processing and coordinate transformation enables the automatic generation of robot targets for multi-step operations, including nut removal and battery module extraction. The results demonstrate that the modular integration of industrial robotics and AI-based perception can enable adaptive, multi-operation battery disassembly in a near-industrial environment. Experimental validation across 36 disassembly trials demonstrates reliable module extraction with a 100% success rate and an overall nut removal success rate of 77.6%, with performance degradation primarily linked to perception-localisation errors for off-axis nut detections.
Båserud, Tilla Egerhei; Johansen, Joakim; Jha, Ajit & Tyapin, Ilya (2026). Dual-Arm Robotic Textile Unfolding with Depth-Corrected Perception and Fold Resolution. Robotics. 15(4). doi: 10.3390/robotics15040078. Full text in Research Archive Show summary
Reliable textile recycling requires automated unfolding to expose hidden hard components such as zippers, buttons, and metal fasteners, which otherwise risk damaging machinery and compromising downstream processes. This paper presents the design and implementation of an automated textile unfolding system based on a dual-arm robotic manipulation framework. The system uses two Interbotix WidowX 250s 6-DoF robotic arms and an Intel RealSense L515 LiDAR camera for visual perception. The unfolding process consists of three stages: initial dual-arm stretching to reduce major folds, refinement through a second stretch targeting the lower region, and a machine-learning stage that employs a YOLOv11 framework trained on depth-encoded textile images, followed by a depth-gradient-based estimator for fold direction. The system applies an extremity-based grasping strategy that selects leftmost and rightmost textile points from a custom error-corrected depth map, enabling robust grasp point selection, and a fold direction estimation method based on depth gradients around the detected fold. The most confident fold region is selected, an unfolding direction is determined using depth ranking, and the textile is manipulated until a flat state is confirmed through depth uniformity. Experiments show that depth correction significantly reduces spatial error in the robot frame, while segmentation and extremity detection achieve high accuracy across varied fold configurations, and the YOLOv11n-based model reaches 98.8% classification accuracy, while fold direction is estimated correctly in 87% of test cases. By enabling robust, largely autonomous textile unfolding, the system demonstrates a practical approach that could support safer and more efficient automated textile recycling workflows.
Brekke, Vegard; Berge, Erlend Odd; Dybdahl, Eirik; Singh, Jayant & Tyapin, Ilya (2026). ROS 2-Driven Navigation and Sensor Platform for Quadruped Robots. Robotics. 15(4). doi: 10.3390/robotics15040070. Full text in Research Archive Show summary
This paper presents an open-source ROS 2 navigation and sensor platform for quadruped robots, demonstrated on Boston Dynamics Spot in a laboratory environment. The platform integrates SLAM Toolbox for mapping and localisation, Navigation2 with MPPI and Smac Hybrid-A* for global path planning, and a frontier-based autonomous exploration module with practical handling of unreachable frontiers. The paper validates and verifies current, open-source algorithms deployed on off-the-shelf hardware. A greedy wavefront-based frontier selection method is presented that prioritizes Time-to-Closest-Viable-Frontier (TCVF) by terminating the search as soon as a feasible frontier is identified. On a real robot dataset replayed across five goal scenarios, the method reduces median selection latency from 94.31 ms to 51.08 ms (95th percentile: 109.54 ms to 56.99 ms), corresponding to a 1.85-times improvement in compute time compared to a standard implementation. The system also employs Zenoh middleware and Foxglove for remote monitoring and control, enabling flexible, high-bandwidth operation. The platform, including configuration files and launch scripts, is released openly to support future research and deployment on quadruped robots.
Økter, Martin Bjaadal; Tyapin, Ilya & Choux, Martin Marie Hubert (2025). Dynamic Robotic Disassembly using Reinforcement Learning and Simulation: Initial Application to EV Batteries. International Conference on Control, Mechatronics and Automation. ISSN 2837-5114. doi: 10.1109/iccma67641.2025.11369636. Full text in Research Archive Show summary
The disassembly of electric vehicle (EV) battery packs remains a labor-intensive and potentially hazardous process, complicated by significant variations in pack design and condition. Conventional automation relies on rigid programming and prior knowledge of component layout, which limits scalability and adaptability. This work presents a proof-of-concept framework for adaptive robotic disassembly using reinforcement learning (RL) and high-fidelity simulation. A simplified two-stage disassembly task—removing a locking pin from a pipe-and-cylinder assembly, was implemented in NVIDIA Isaac Sim and integrated with the Isaac Lab RL environment. Proximal Policy Optimization (PPO) agents were trained using both the RSL-RL and StableBaselines3 libraries, employing structured reward shaping, targeted hyperparameter tuning, and Cartesian end-effector control to improve learning stability and task precision. Initial results demonstrate consistent task completion, with reduced unintended movement of non-target components and high repeatability across validation runs. The developed simulation and training pipeline provides a flexible, modular platform for future exploration of alternative RL algorithms and more complex disassembly scenarios. These results highlight the potential of RL-based methods to enable scalable, dynamic automation for EV battery recycling in environments with high variability and uncertainty.
Halvorsen, Torbjørn Seim; Tyapin, Ilya & Jha, Ajit (2025). Autonomous Textile Sorting Facility and Digital Twin Utilizing an AI-Reinforced Collaborative Robot. Electronics (Basel). 14(13). doi: 10.3390/electronics14132706. Full text in Research Archive Show summary
This paper presents the design and implementation of an autonomous robotic facility for textile sorting and recycling, leveraging advanced computer vision and machine learning technologies. The system enables real-time textile classification, localization, and sorting on a dynamically moving conveyor belt. A custom-designed pneumatic gripper is developed for versatile textile handling, optimizing autonomous picking and placing operations. Additionally, digital simulation techniques are utilized to refine robotic motion and enhance overall system reliability before real-world deployment. The multi-threaded architecture facilitates the concurrent and efficient execution of textile classification, robotic manipulation, and conveyor belt operations. Key contributions include (a) dynamic and real-time textile detection and localization, (b) the development and integration of a specialized robotic gripper, (c) real-time autonomous robotic picking from a moving conveyor, and (d) scalability in sorting operations for recycling automation across various industry scales. The system progressively incorporates enhancements, such as queuing management for continuous operation and multi-thread optimization. Advanced material detection techniques are also integrated to ensure compliance with the stringent performance requirements of industrial recycling applications.
Bilal, Muhammad Talha; Tian, Doris Siyu; Choux, Martin Marie Hubert; Jiao, Lei & Tyapin, Ilya (2025). Optimizing Automated Battery Demanufacturing Through Simulation-Based Analysis and Genetic Algorithm. Robotics. 14(11). doi: 10.3390/robotics14110156. Full text in Research Archive Show summary
The automation of recycling processes for electric vehicle lithium-ion battery packs is crucial for the advancement of green energy transportation. Testing disassembly strategies on real equipment is time consuming, expensive, and poses significant safety risks. This paper presents a novel simulation-based framework that leverages the integration of a high-fidelity virtual environment with a Robot Operating System (ROS) to visualize and accurately calculate the time required for complex robotic disassembly operations. The calculated operation times are then used as input for genetic algorithm optimization to improve process efficiency. The results demonstrate that automation significantly improves the total speed of the disassembly process compared to manual methods. By utilizing this novel simulation and optimization approach, a 25% improvement in performance was achieved for the pack-to-module disassembly stage. This method provides a safe and cost-effective approach for process design, contributing directly to the development of a circular economy and supporting the transition towards sustainable transportation.
Bilal, Muhammad Talha; Tyapin, Ilya & Choux, Martin Marie Hubert (2023). Fusion of Multiview Images for EV Battery Disassembly. In Zhou, Jing (Eds.), 2023 11th International Conference on Control, Mechatronics and Automation (ICCMA). IEEE (Institute of Electrical and Electronics Engineers). ISSN 9798350315684. p. 19–24. doi: 10.1109/ICCMA59762.2023.10374794. Full text in Research Archive Show summary
Automation in Electric Vehicle (EV) Li-Ion Battery (LIB) pack disassembly is getting a lot of attraction with increased number of EVs being manufactured. Highly cluttered components placed in complex configurations present a unique challenge for object detection models. To get maximum coverage of the components in the EV battery pack, images from multiple viewpoints are considered and merged using Multiple-View Super Resolution (MVSR). The proposed method provides 7% higher accuracy in the screw detection task than the statistical methods previously derived [[1]].
Singh, Jayant; Zhou, Jing; Beferull-Lozano, Baltasar & Tyapin, Ilya (2022). Learning Cooperative Multi-Agent Policies with Multi-Channel Reward Curriculum Based Q-Learning. Proceedings of the Annual Conference of the IEEE Industrial Electronics Society (IECON). ISSN 1553-572X. doi: 10.1109/IECON49645.2022.9969046. Full text in Research Archive Show summary
Multi-Agent Reinforcement Learning (MARL) algorithms based on the Centralised Training Decentralised Execution (CTDE) approach have seen a great deal of interest in recent years. Most of the recent works focus on a specific class of environments built on the StartCraft Multi-Agent Challenge (SMAC) environment suite. However, experiments with the PettingZoo multi-particle environments show poor performance in an interesting subset of tasks. In this paper, the nature of these environments and the reward structures are analyzed. It shows that poor performance in these tasks is not due to a lack of representation power in the individual Q function or mixing functions, but rather a result of convergence to a suboptimal equilibrium of dual channel rewards and the issue of agent-reward decoupling that can be a common problem for many MARL environments. We present reward curriculum-based versions of QMIX and VDN as a solution to these problems and compare their results with the standard algorithms. The results show a clear performance gain in terms of a common cumulative reward metric.
Subedi, Dipendra; Aune, Teodor N.; Tyapin, Ilya & Hovland, Geir (2022). Static Deflection Compensation of Multi-Link Flexible Manipulators Under Gravity. IEEE Access. 10, p. 9658–9667. doi: 10.1109/ACCESS.2022.3144404. Full text in Research Archive Show summary
The static deflection compensation method of a planar multi-link flexible manipulator is proposed using the feedback from inertial sensors mounted at the tip of each link. The proposed compensation technique is validated experimentally using a high-precision laser tracker. The proposed strategy is experimentally verified using a three-link flexible manipulator. A strategy to compensate for the centripetal and tangential acceleration induced on the accelerometer mounted on the rotating link is proposed for correct inclination estimation. The improvement in the inclination estimation using the proposed compensation technique is verified both in simulation and experimental studies.
Bilal, Muhammad Talha; Tyapin, Ilya & Choux, Martin Marie Hubert (2022). Enhancing Object Localization Accuracy by using Multiple Camera Viewpoints for Disassembly Systems, IECON 2022 – 48th Annual Conference of the IEEE Industrial Electronics Society. IEEE (Institute of Electrical and Electronics Engineers). ISSN 9781665480253. doi: 10.1109/IECON49645.2022.9968575. Full text in Research Archive Show summary
The number of images taken from different view-points plays an important role in the accuracy of object detection in cluttered scenarios. Considering Electric Vehicles battery pack disassembly task, which is a highly dense clutter, a framework is proposed to approximate the number of viewpoints to acquire the accuracy of 3.82 mm in screw detection. The paper explores two methods of image acquisition i) taking multiple 3D images, and ii) taking one 3D image and multiple 2D images and combines it with two methods of image processing i) marking the exact visible center of the screw for calculation, and ii) using a bounding box to mark the screw and calculating the center by intersecting diagonals. The results show that using eight viewpoints with a reliable 3D camera delivers the optimal results.
Subedi, Dipendra; Tyapin, Ilya & Hovland, Geir (2022). Control of Redundant Flexible Manipulators with Redundancy Resolution. In IEEE, . (Eds.), The 8th International Conference on Mechatronics and Robotics Engineering (ICMRE). IEEE (Institute of Electrical and Electronics Engineers). ISSN 9781665483773. p. 116–121. doi: 10.1109/ICMRE54455.2022.9734097. Full text in Research Archive Show summary
This paper deals with the online control of a redundant flexible link manipulator to achieve minimum oscillations using the redundancy resolution technique. Different redundancy resolution techniques proposed and used for rigid link manipulators are tested for their use in the case of flexible link manipulators. The simulation model of a planar three-link flexible manipulator is used in this study. The redundancy resolution using kinetic energy minimization techniques is compared with the local joint acceleration minimization method to show the advantage of achieving minimum vibrations. Keywords—Elasticity, flexibility, redundant manipulator, redundancy resolution, vibration, optimization.
Subedi, Dipendra; Tyapin, Ilya & Hovland, Geir (2021). Dynamic Modeling of Planar Multi-Link Flexible Manipulators. Robotics. 10(2). doi: 10.3390/robotics10020070. Full text in Research Archive Show summary
A closed-form dynamic model of the planar multi-link flexible manipulator is presented. The assumed modes method is used with the Lagrangian formulation to obtain the dynamic equations of motion. Explicit equations of motion are derived for a three-link case assuming two modes of vibration for each link. The eigenvalue problem associated with the mass boundary conditions, which changes with the robot configuration and payload, is discussed. The time-domain simulation results and frequency-domain analysis of the dynamic model are presented to show the validity of the theoretical derivation.
Jakobsen, Mette Mo; Tørdal, Sondre Sanden; Klausen, Andreas; Robbersmyr, Kjell Gunnar & Tyapin, Ilya (2021). Product development and project-based learning in Mechatronics, in the context of digitization and sustainability. Nordic Journal of STEM Education. 5(1). doi: 10.5324/njsteme.v5i1.3946. Full text in Research Archive
Choux, Martin Marie Hubert; Bigorra, Eduard Marti & Tyapin, Ilya (2021). Task Planner for Robotic Disassembly of Electric Vehicle Battery Pack. Metals. 11(3). doi: 10.3390/met11030387. Full text in Research Archive
Subedi, Dipendra; Tyapin, Ilya & Hovland, Geir (2020). Modeling and Analysis of Flexible Bodies Using Lumped Parameter Method. In Kuppuswamy, Ramesh (Eds.), Proceedings of the 2020 IEEE 11th International Conference on Mechanical and Intelligent Manufacturing Technologies. IEEE (Institute of Electrical and Electronics Engineers). ISSN 9781728153322. doi: 10.1109/ICMIMT49010.2020.9041188. Full text in Research Archive Show summary
The modeling, identification and analysis of a flexible beam is presented. The lumped parameter method is used to model a flexible beam. The use of camera measurements to identify lumped parameters, namely spring stiffness and damping coefficient, is described. The measurements of the tip oscillations using a high-speed camera and high-precision laser tracker are compared. The static and dynamic behavior of the flexible beam model is compared to the experimental results to show the validity of the model.
Jha, Ajit; Subedi, Dipendra; Løvsland, Per-Ove; Tyapin, Ilya; Cenkeramaddi, Linga Reddy & Beferull-Lozano, Baltasar [Show all 7 contributors for this article] (2020). Autonomous mooring towards autonomous maritime navigation and offshore operations, 15th IEEE Conference on Industrial Electronics and Applications. Institute of Electrical and Electronics Engineers (IEEE). ISSN 9781728151687. p. 1171–1175. doi: 10.1109/ICIEA48937.2020.9248169. Full text in Research Archive Show summary
Bollard is a vital component of mooring system. It is the anchor point for mooring ropes to be fixed in order to secure the vessel or ship. An algorithm that translates the segmented mask of bollard output from masked R-CNN along with bounding box and associated class probability to its corresponding edge coordinate and finally to the single reference point for efficient detection and classification of bollard towards autonomous mooring is presented. At first stage, Mask R-CNN framework is trained with custom built bollard. The model obtained from the training is inferred with real data resulting in instance segment of bollard. The segmented mask obtained contains relatively large amount of the data points representing the whole area of bollard, which typically is not desirable. In order to precisely localize the bollard with one reference co-ordinate, the proposed algorithm is applied to segmented mask. Firstly, it translates the segmented mask to only four co-ordinate points, where each point correspond to the edge of bollard. Further, from the edges, the reference point is estimated. This causes significant reduction in point of interest (POI) and has potential to reduce the error encountered during pose estimation of the bollard in 3D thus making the autonomous mooring more precise and accurate.
Subedi, Dipendra; Jha, Ajit; Tyapin, Ilya & Hovland, Geir (2020). Camera-LiDAR Data Fusion for Autonomous Mooring Operation. IEEE Conference on Industrial Electronics and Applications. p. 1176–1181. doi: 10.1109/ICIEA48937.2020.9248089. Full text in Research Archive Show summary
The use of camera and LiDAR sensors to sense the environment has gained increasing popularity in robotics. Individual sensors, such as cameras and LiDARs, fail to meet the growing challenges in complex autonomous systems. One such scenario is autonomous mooring, where the ship has to be tied to a fixed rigid structure (bollard) to keep it stationary safely. The detection and pose estimation of the bollard based on data fusion from the camera and LiDAR are presented here. Firstly, a single shot extrinsic calibration of LiDAR with the camera is presented. Secondly, the camera-LiDAR data fusion method using camera intrinsic parameters and camera to LiDAR extrinsic parameters is proposed. Finally, the use of an image-based segmentation method to segment the corresponding point cloud from the fused camera-LiDAR data is developed and tailored for its application in autonomous mooring operation.
Subedi, Dipendra; Tyapin, Ilya & Hovland, Geir (2020). Review on Modeling and Control of Flexible Link Manipulators. MIC Journal: Modeling, Identification and Control. ISSN 0332-7353. 41(3), p. 141–163. doi: 10.4173/mic.2020.3.2. Full text in Research Archive
Brunete, Alberto; Gambao, Ernesto; Koskinen, Jukka; Heikkila, Tapio; Kaldestad, Knut Berg & Tyapin, Ilya [Show all 11 contributors for this article] (2018). Hard material small-batch industrial machining robot. Robotics and Computer-Integrated Manufacturing. ISSN 0736-5845. 54, p. 185–199. doi: 10.1016/j.rcim.2017.11.004. Full text in Research Archive
Tyapin, Ilya & Hovland, Geir (2018). Long Arm Manipulator Path Interpolation Using 4th Order B-Splines. In -, IEEE (Eds.), International Conference on Control, Automation and Systems (ICCAS), 18th. IEEE (Institute of Electrical and Electronics Engineers). ISSN 9788993215168. Full text in Research Archive
Tyapin, Ilya; Berntsen, Kai Egil & Bertheussen, André (2018). Combined Stiffness Identification of 6-DoF Industrial Robot. In -, IEEE (Eds.), International Conference on Control, Automation and Systems (ICCAS), 18th. IEEE (Institute of Electrical and Electronics Engineers). ISSN 9788993215168. Full text in Research Archive
Tørdal, Sondre Sanden; Hovland, Geir Edvin & Tyapin, Ilya (2017). Efficient Implementation of Inverse Kinematics on a 6-DOF Industrial Robot using Conformal Geometric Algebra. Advances in Applied Clifford Algebras. ISSN 0188-7009. 27(3), p. 2067–2082. doi: 10.1007/s00006-016-0698-2. Full text in Research Archive Show summary
This paper presents an implementation of the inverse kinematics (IK) solution for an industrial robot based on Conformal Geometric Algebra where the correct signs of the joint angles are extracted using the multivector coefficients and applying the forward kinematics. The solution presented is twice as fast as traditional IK algorithms implemented using matrix algebra, and more than 45 times faster than the IK provided by the robot manufacturer. The proposed solution has been successfully demonstrated and benchmarked in a 3-DOF motion compensation experiment. In addition to being efficient the presented solution requires less matrix operations than for the traditional IK.
Sandberg, Marcus; Tyapin, Ilya; Kokkolaras, Michael; Lundbladh, Anders & Isaksson, Ola (2017). A knowledge-based master model approach exemplified with jet engine structural design. Computers in industry (Print). ISSN 0166-3615. 85, p. 31–38. doi: 10.1016/j.compind.2016.12.003. Full text in Research Archive
Kaldestad, Knut Berg; Tyapin, Ilya & Hovland, Geir (2015). Robotic face milling path correction and vibration reduction, 2015 IEEE International Conference on Advanced Intelligent Mechatronics (AIM 2015). Curran Associates, Inc.. ISSN 9781467391085. p. 543–548. doi: 10.1109/AIM.2015.7222591. Full text in Research Archive
Tyapin, Ilya; Kaldestad, Knut Berg & Hovland, Geir (2015). Off-line path correction of robotic face milling using static tool force and robot stiffness, 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2015). Curran Associates, Inc.. ISSN 9781479999958. p. 5506–5511. doi: 10.1109/IROS.2015.7354157. Full text in Research Archive
Tyapin, Ilya; Hovland, Geir & Brogårdh, Torgny (2014). Method for Estimating Combined Controller, Joint and Link Stiffnesses of an Industrial Robot. In NN, NN (Eds.), 2014 IEEE International Symposium on Robotic and Sensors Environments (ROSE). Curran Associates, Inc.. ISSN 9781479949250. doi: 10.1109/ROSE.2014.6952974. Full text in Research Archive
Tyapin, Ilya; Hovland, Geir; Kosonen, Petri & Linna, Tarmo (2014). Identiﬁcation of a Static Tool Force Model for Robotic Face Milling, 2014 IEEE/ASME 10th International Conference on Mechatronic and Embedded Systems and Applications(MESA). IEEE (Institute of Electrical and Electronics Engineers). ISSN 9781479922802. doi: 10.1109/MESA.2014.6935591. Full text in Research Archive
Tyapin, Ilya & Hovland, Geir (2013). Kinematic calibration method for a 5-DOF Gantry-Tau parallel kinematic machine. IEEE International Conference on Robotics and Automation (ICRA). ISSN 1050-4729. p. 4665–4670. doi: 10.1109/ICRA.2013.6631241. Full text in Research Archive Show summary
In this paper a new step-wise approach to kinematic calibration of a 5-DOF Gantry-Tau parallel kinematic machine (PKM) is presented. The approach can be adapted to the modular design of the PKM and the calibration could easily perform part of the assembly instructions for the machine. By using measurements from a laser tracker and least-squares estimates of polynomial functions, a typical accuracy of about 20 micrometer was achieved for the base actuators. The remaining set of 30 general parameters for the hexapod link structure and spherical joint connections were successfully estimated using the Complex search-based evolutionary algorithm.
Nguyen, Trinh Hoang; Prinz, Andreas; Friisø, Trond; Nossum, Rolf Tomas & Tyapin, Ilya (2013). A framework for data integration of offshore wind farms. Renewable Energy. ISSN 0960-1481. 60, p. 150–161. doi: 10.1016/j.renene.2013.05.002. Full text in Research Archive Show summary
Operation and maintenance play an important role in maximizing the yield and minimizing the downtime of wind turbines, especially offshore wind farms where access can be difficult due to harsh weather conditions for long periods. It contributes up to 25–30% to the cost of energy generation. Improved operation and maintenance (O&M) practices are likely to reduce the cost of wind energy and increase safety. In order to optimize the O&M, the importance of data exchange and knowledge sharing within the offshore wind industry must be realized. With more data available, it is possible to make better decisions, and thereby improve the recovery rates and reduce the operational costs. This article describes the development of a framework for data integration to optimize the remote operations of offshore wind farms.
Haaø, Jørgen; Vangen, Steffen; Tyapin, Ilya; Choux, Martin Marie Hubert; Hovland, Geir & Hansen, Michael Rygaard (2012). The Effect of Friction in Passive and Active Heave Compensation of Crown Block Mounted Compensators. In Imsland, Lars Struen (Eds.), 2012 IFAC Workshop on Automatic Control in Offshore Oil and Gas Production : Norwegian University of Science and Technology 31.5-1.6 2012. Elsevier. ISSN 9783902661999. doi: 10.3182/20120531-2-no-4020.00040. Full text in Research Archive Show summary
This paper studies the effects of friction model during passive and active heave compensation of offshore drilling equipment. The main purpose of heave compensation while drilling from vessels or semi-submersible platforms is to maintain the drilling operation unaffected by the wave induced motion. The investigated system is of an existing crown mounted compensator. A model of the system is developed which includes mechanics, hydraulics and pneumatics. The passive heave compensation scheme is described including force equalising hydraulic cylinders. In this paper the detrimental effect of friction on the heave compensation performance in both passive and active heave compensation is investigated and discussed.
Kjelland, Magnus Berthelsen; Hansen, Michael Rygaard; Tyapin, Ilya & Hovland, Geir (2012). Tool-Point Control for a Redundant Heave Compensated Hydraulic Manipulator. In Imsland, Lars Struen (Eds.), 2012 IFAC Workshop on Automatic Control in Offshore Oil and Gas Production : Norwegian University of Science and Technology 31.5-1.6 2012. Elsevier. ISSN 9783902661999. doi: 10.3182/20120531-2-no-4020.00034. Full text in Research Archive Show summary
In this paper, theoretical and experimental implementation of heave compensation on a redundant hydraulically actuated manipulator with 3-dof has been carried out. The redundancy is solved using the pseudo-inverse Jacobian method. Techniques for minimizing velocities and avoiding mechanical joint saturations is implemented in the null space joint motion. Model based feed-forward, combined with a PI-controller handles the velocity control of each joint.A time domain simulation model has been developed, experimentally verified, and used for controller parameter tuning. Model verification and experimental results are obtained while the manipulator is exposed to wave disturbances created in a dry environment by means of a Stewart platform.
Choux, Martin Marie Hubert; Tyapin, Ilya & Hovland, Geir (2012). Leakage-detection in blade pitch control systems for wind turbines, Reliability and Maintainability Symposium (RAMS), 2012 Proceedings. IEEE (Institute of Electrical and Electronics Engineers). ISSN 9781457718519. doi: 10.1109/rams.2012.6175515. Full text in Research Archive Show summary
The main contribution of the work is a systematic study evaluating the performance of different filters for leakage detection in pitch control systems. The effectiveness of the proposed methods is examined in a Matlab/Simulink real-time environment. The test bed consists of the following elements: hydraulic power unit, servo valve, two leakage bypasses, hydraulic cylinder, payload and xPC-based control system. The filters are tested with the state-augmentation and the hypothesis testing approaches. To our knowledge, the comparison of these different approaches has not been done previously for this type of application. The paper concludes on the accuracy and sensitivity of the leakage detection as well as the computational complexity and the real-time performance.
Choux, Martin Marie Hubert; Tyapin, Ilya & Hovland, Geir (2012). Extended friction model of a hydraulic actuated system, Reliability and Maintainability Symposium (RAMS), 2012 Proceedings. IEEE (Institute of Electrical and Electronics Engineers). ISSN 9781457718519. doi: 10.1109/rams.2012.6175517. Full text in Research Archive Show summary
The main contribution of this paper is an experimental validation and comparison of three different friction models for an electro-hydraulic servo system. The first is the wellknown LuGre model which incorporates dynamic friction effects. The second model is based on a relatively recent publication by Yanada in 2008 [6], which incorporates liquid film thickness in the servo valve. The third model is a new contribution presented in this paper, where valve underlap and mass acceleration are combined with the LuGre model. The experimental results show that for hydraulic systems, the film thickness model is an improvement over the LuGre model, while the new model presented in this paper is an improvement over both the LuGre and the film thickness models. An accurate friction model is an important tool for reliability engineers when distinguishing maintenance related degradation from dynamic effects.
Kjelland, Magnus Berthelsen; Hansen, Michael Rygaard; Tyapin, Ilya & Hovland, Geir (2012). Tool-Point Control of a Planar Hydraulically Actuated Manipulator with Compensation of Non-Actuated Degree of Freedom, 2012 12th International Conference on Control, Automation and Systems, Proceedings. IEEE (Institute of Electrical and Electronics Engineers). ISSN 9788993215045. p. 672–677. Full text in Research Archive Show summary
The current work is on motion control of a hydraulically actuated manipulator with a view to handle offshore payload transfer between moving frames. The manipulator has redundant actuation and also, a non-actuated degree of freedom. The motion control has two targets: tool point control and compensation of the non-actuated degree of freedom. The redundancy is handled by means of pseudo-inverse kinematics while optimizing a cost function, avoiding mechanical joint limits. The compensation of the un-actuated degree of freedom employs LQR control, minimizing position and velocity error while maintaining the tracking reference for the tool-point. The proposed control scheme is implemented and experimentally validated in a practical system where the manipulator is mounted on a Stewart platform that allows for the simulation of wave induced heave motion as a disturbance.
Sandberg, Marcus; Tyapin, Ilya; Kokkolaras, Michael & Isaksson, Ola (2011). A knowledge-based master modeling approach to system analysis and design. In Howard, Thomas; Mougaard, Krestine; McAloone, Timothy Charles & Hansen, Claus Thorp (Ed.), Proceedings of the 18th International Conference on Engineering Design (ICED11), 15-18 Aug 2011. The Design Society. ISSN 9781904670322. p. 347–356. Full text in Research Archive
Tyapin, Ilya; Hovland, Geir & Jorde, Jørgen (2011). Comparison of Markov Theory and Monte Carlo Simulations for Analysis of Marine Operations Related to Installation of an Offshore Wind Turbine. In Singh, Maneesh; N., Rao Raj B. K. & Liyanage, Jayantha Prasanna (Ed.), Proceedings of the 24th International Congress on Condition Monitoring and Diagnostics Engineering Management (COMADEM2011). COMADEM International. ISSN 9780954130725. p. 1071–1081. Full text in Research Archive Show summary
This paper contains a comparison study of two different methods for estimating weather downtime and duration of marine operations related to the installation of bottom-fixed offshore wind turbines. The first method is based on numerical Monte Carlo simulations. The second method is based on an approach using Markov theory as published in (Anastasiou and Tsekos, 1996), and it differs from the Monte Carlo technique in that it establishes analytically, not through simulation, the probability distribution of the duration of the marine operations. Having established the probability distribution of individual activities in the operations scenario, the probability distribution of the duration of an entire marine operation is determined with the aid of the Probabilistic Network and Evaluation Technique (PNET), see (Ang et al., 1975). The combination of Markov theory and PNET provides a useful means for predicting the duration of a marine operation. Both activities which do and do not require a weather window are included in the analysis, as well as the possibility to execute activities as a combination of parallel and sequential operations. A comparison of the computational time efforts using the analytical approach and Monte Carlo simulation are presented in in this paper, where Markov theory based approach is several times faster than Monte Carlo simulations. The paper includes an illustrative example related to the installation process of bottom-fixed offshore wind turbines.. The sea state generator used in the example is based on observed weather data for the North Sea. The paper concludes with a summary of advantages and disadvantages of the two approaches based on Monte Carlo simulations and Markov Theory/PNET.
Sandberg, Marcus; Tyapin, Ilya; Kokkolaras, Michael; Isaksson, Ola; Aidanpää, Jan-Olov & Larsson, Tobias (2011). A Knowledge-based Master-model Approach with Application to Rotating Machinery Design. Concurrent Engineering: Research and Applications (CERA). ISSN 1063-293X. 19(4), p. 295–305. doi: 10.1177/1063293X11424511. Full text in Research Archive Show summary
Novel rotating machinery design concepts and architectures are being explored to reduce mass, energy consumption, manufacturing costs, and environmental impact while increasing performance. As component manufacturers supply parts to original equipment manufacturers, it is desirable to design the components using a systems approach so that they are optimized for system-level performance. To accomplish that, suppliers must be able to model and predict the behavior of the whole machinery. Traditional computer-aided design/computer-aided engineering master-modeling approaches enable manual changes to be propagated to linked models. Novel knowledge-based master-modeling approaches enable automated coordination of multidisciplinary analyses. In this article, we present a specific implementation of such a knowledge-based master-modeling approach that facilitates multidisciplinary design optimization of rotating machinery. The master-model (MM) approach promotes the existence of a single governing version of the product definition as well as operating scenarios. Rules, scripts, and macros link the MM to domain-specific models. A simple yet illustrative industry application is presented, where rotor-dynamics and displacement analyses are performed to evaluate relocation alternatives for the rear bearing position of a rotating machinery under a ‘fan-blade-off’ load case.

View all works in NVA

Robsrud, Didrik Nicolai; Ovsthus, Orjan; Muggerud, Lars; Andrade, José Amendola Netto; Cenkeramaddi, Linga Reddy & Tyapin, Ilya [Show all 7 contributors for this article] (2023). Lidar-mmW Radar Fusion for Safer UGV Autonomous Navigation with Collision Avoidance. In Zhou, Jing (Eds.), 2023 11th International Conference on Control, Mechatronics and Automation (ICCMA). IEEE (Institute of Electrical and Electronics Engineers). ISSN 9798350315684. doi: 10.1109/ICCMA59762.2023.10375017. Full text in Research Archive
Øvsthus, Ørjan; Robsrud, Didrik Nicolai; Muggerud, Lars; Andrade, José Amendola Netto; Cenkeramaddi, Linga Reddy & Tyapin, Ilya [Show all 7 contributors for this article] (2023). Mobile Robotic Manipulator Based Autonomous Warehouse Operations. In Zhou, Jing (Eds.), 2023 The 11th International Conference on Control, Mechatronics and Automation (ICCMA 2023). IEEE (Institute of Electrical and Electronics Engineers). ISSN 9781665490481. doi: 10.1109/ICCMA59762.2023.10374743. Full text in Research Archive
Ovsthus, Orjan; Robsrud, Didrik Nicolai; Muggerud, Lars; Amendola, José; Cenkeramaddi, Linga Reddy & Tyapin, Ilya [Show all 7 contributors for this article] (2023). Mobile Robotic Manipulator based Autonomous Warehouse Operations. Full text in Research Archive
Robsrud, Didrik Nicolai; Ovsthus, Orjan; Muggerud, Lars; Amendola, José; Cenkeramaddi, Linga Reddy & Tyapin, Ilya [Show all 7 contributors for this article] (2023). Lidar-mmW Radar Fusion for Safer UGV Autonomous Navigation with Collision Avoidance. Full text in Research Archive
Jakobsen, Mette Mo; Tørdal, Sondre Sanden; Klausen, Andreas; Robbersmyr, Kjell Gunnar & Tyapin, Ilya (2021). Product development and project-based learning in Mechatronics, in the context of digitization and sustainability. Full text in Research Archive
Jha, Ajit; Subedi, Dipendra; Løvsland, Per-Ove; Tyapin, Ilya; Cenkeramaddi, Linga Reddy & Beferull-Lozano, Baltasar [Show all 7 contributors for this article] (2020). Autonomous mooring towards autonomous maritime navigation and offshore operations. Full text in Research Archive
Subedi, Dipendra & Tyapin, Ilya (2022). Modeling and Control of Flexible Link Manipulators. Universitetet i Agder. ISSN 9788284270838. Full text in Research Archive Show summary
Autonomous maritime navigation and offshore operations have gained wide attention with the aim of reducing operational costs and increasing reliability and safety. Offshore operations, such as wind farm inspection, sea farm cleaning, and ship mooring, could be carried out autonomously or semi-autonomously by mounting one or more long-reach robots on the ship/vessel. In addition to offshore applications, long-reach manipulators can be used in many other engineering applications such as construction automation, aerospace industry, and space research. Some applications require the design of long and slender mechanical structures, which possess some degrees of flexibility and deflections because of the material used and the length of the links. The link elasticity causes deflection leading to problems in precise position control of the end-effector. So, it is necessary to compensate for the deflection of the long-reach arm to fully utilize the long-reach lightweight flexible manipulators. This thesis aims at presenting a unified understanding of modeling, control, and application of long-reach flexible manipulators. State-of-the-art dynamic modeling techniques and control schemes of the flexible link manipulators (FLMs) are discussed along with their merits, limitations, and challenges. The kinematics and dynamics of a planar multi-link flexible manipulator are presented. The effects of robot configuration and payload on the mode shapes and eigenfrequencies of the flexible links are discussed. A method to estimate and compensate for the static deflection of the multi-link flexible manipulators under gravity is proposed and experimentally validated. The redundant degree of freedom of the planar multi-link flexible manipulator is exploited to minimize vibrations. The application of a long-reach arm in autonomous mooring operation based on sensor fusion using camera and light detection and ranging (LiDAR) data is proposed.
Zhou, Jing; Vange, Tom Erik & Tyapin, Ilya (2021). Model-free object grasping : Model-free object grasping with a learning-free approach. Universitetet i Agder. Full text in Research Archive Show summary
The industry standards and capability are constantly advancing and pushing forward to increase data collection, efficiency, profit, and quality as well as decrease downtime, injuries, and hazards as much as possible. In recent years, robot systems have received more attention in the context of a large number of industrial applications, such as automotive manufacturing, additive manufacturing, assembly, quality inspection, and co-packing. The collaboration between multiple robots and human operators is considered to be the most prominent strategy in Industry 4.0 and future Industry 5.0, sharing the same space and collaborating on tasks according to their complementary capabilities. With the use of robots and their abilities could efficiency, profit, safety, and quality be further increased, potentially revolutionizing the industry and production. This project was supported in part by DEEPCOBOT Project. DEEPCOBOT, Collective Efficient Deep Learning and Networked Control for Multiple Collaborative Robot Systems, are a research project funded by IKTPLUSS under Grant 306640/O70 from the Research Council of Norway. The project will investigate the design of a new generation of decentralized data-driven Deep Learning based controllers for multiple coexisting collaborative robots, which interact both between them-selves and with human operators in order to collectively learn from each other’s experiences and perform cooperatively different complex tasks in large-scale industrial environments. This is motivated by the increasing demand of automation in industry, especially the demand of a safer and more efficient collaboration between multiple robots and human operators to integrate the best of human abilities and robotic automation.
Zhou, Jing; Kumar, Ravi; Radicke, Jan-Philip; Eidhammer, Eirik & Tyapin, Ilya (2021). Multi-Robot Cell Operation using Robot Operating System. Universitetet i Agder. Full text in Research Archive
Zhou, Jing; Ims, Benjamin Årøy; Enehaug, Bjørn; Skår, Eirik Magnus & Tyapin, Ilya (2021). HUMAN-COBOT SEQUENTIAL COOPERATION. Universitetet i Agder. Full text in Research Archive

View all works in NVA

Published Apr. 16, 2024 11:41 AM