A5090081010- Fault Detection and Control Systems
- Machine Fault Diagnosis Techniques
- Wind Turbine Control Systems
- Structural Health Monitoring Techniques
- Robot Manipulation and Learning
- Robotic Path Planning Algorithms
- Advanced Control Systems Optimization
- Wind Energy Research and Development
- Hydraulic and Pneumatic Systems
- Energy Load and Power Forecasting
- Soft Robotics and Applications
- Real-time simulation and control systems
- Cavitation Phenomena in Pumps
- Inertial Sensor and Navigation
- Control Systems and Identification
- Oil and Gas Production Techniques
- Kidney Stones and Urolithiasis Treatments
- Ultrasound in Clinical Applications
- Robotic Mechanisms and Dynamics
- Flow Measurement and Analysis
- Teleoperation and Haptic Systems
- Anatomy and Medical Technology
- Augmented Reality Applications
- Power System Reliability and Maintenance
- Surgical Simulation and Training
University of Ferrara
2016-2025
The fault diagnosis of wind farms has been proven to be a challenging task, and motivates the research activities carried out through this work. Therefore, paper deals with park benchmark model, it considers viable solutions problem earlier detection isolation. design indicator involves data-driven approaches, as they can represent effective tools for coping poor analytical knowledge system dynamics, noise, uncertainty, disturbances. In particular, proposed rely on fuzzy models neural...
In order to improve the availability of wind turbines and avoid catastrophic consequences, detection faults in their earlier occurrence is fundamental. This paper proposes development a fault diagnosis scheme relying on identified fuzzy models. The theory exploited since it allows approximating uncertain models managing noisy data. These models, form Takagi-Sugeno prototypes, represent residual generators used for isolation (FDI). A turbine benchmark validate achieved performances designed...
The prediction of remaining useful life is critical in predictive health management. This done to reduce the expenses associated with operation and maintenance by avoiding errors failures dynamic processes. Recently, abilities feature classification automated extraction neural networks its convolutional forms have shown fascinating performance when used for estimating processes using deep learning structures. was accomplished putting these talents task predicting how long procedures would be...
The paper describes a control architecture for industrial robotic applications allowing human/robot interactions, using an admittance scheme and direct sensing of the human inputs. aim proposed is to support operator robot, equipped with force/torque (F/T) sensor on end-effector, during collaboration tasks involving heavy payloads carried by robot. In these practical applications, dynamics load may significatively affect measurements F/T sensor. Model-based compensation such dynamic effects...
Abstract This paper deals with the fault diagnosis of wind turbines and investigates viable solutions to problem earlier detection isolation. The design indicator, i.e., estimate, involves data-driven approaches, as they can represent effective tools for coping poor analytical knowledge system dynamics, together noise disturbances. In particular, proposed rely on fuzzy systems neural networks that are used describe strongly nonlinear relationships between measurement faults. chosen...
Percutaneous nephrolithotomy (PCNL) is considered the gold standard for treatment of patients with renal stones larger than 20 mm in diameter. The success and outcomes surgery are very well known to be highly dependent on precision accuracy puncture step, since it must allow reach stone a precise direct path. Thus, performing access during PCNL most crucial challenging step procedure steepest learning curve. In this letter, we propose an innovative solution, based AR application combined...
This paper presents a mobile manipulation platform designed for autonomous depalletizing tasks. The proposed solution integrates machine vision, control and mechanical components to increase flexibility ease of deployment in industrial environments such as warehouses. A collaborative robot mounted on base is proposed, equipped with simple tool 3D in-hand vision system that detects parcel boxes pallet, pulls them one by the transportation. setup allows avoid cumbersome implementation...
The paper addresses the problem of generation collision-free trajectories for a robotic manipulator, operating in scenario which obstacles may be moving at non-negligible velocities. In particular, aims to present trajectory solution that is fully executable real-time and can reactively adapt both dynamic changes environment fast reconfiguration task. proposed motion planner extends method based on dynamical system cope with peculiar kinematics surgical robots laparoscopic operations,...
Nowadays Robotic assisted Minimally Invasive Surgeries (R-MIS) are the elective procedures for treating highly accurate and scarcely invasive pathologies, thanks to their ability empower surgeons' dexterity skills. The research on new Multi-Robots Surgery (MRS) platform is cardinal development of a SARAS surgical robotic platform, which aims at carrying out autonomously assistants tasks during R-MIS procedures. In this work, we will present MRS validation protocol, framed in order assess:...
Point of care ultrasonography and the related focused assessment with sonography for trauma protocol, if performed by experienced physicians, is a highly sensitive examination, specific detection free fluids. Different systems methods have been proposed training, including simulation as one most efficient. This paper presents an ultrasound training system, specifically designed to be used during bedside high fidelity scenarios, that could facilitate learning process. The development system...
In order to improve the availability of wind turbines, thus improving theirefficiency, it is important detect and isolate faults in their earlier occurrence. The mainproblem model-based fault diagnosis applied turbines represented by thesystem complexity, as well reliability available measurements. this work, adata-driven strategy relying on fuzzy models presented, build a diagnosissystem. Fuzzy theory jointly with Frisch identification scheme for errors-in-variablemodels exploited here,...
The fault diagnosis of safety critical systems such as wind turbine installations includes extremely challenging aspects that motivate the research issues considered in this paper. Therefore, work investigates two solutions exploit direct estimation faults by means data-driven approaches. In way, diagnostic residuals are represented reconstructed affecting monitored process. proposed methodologies based on fuzzy and neural networks used to estimate nonlinear dynamic relations between input...
Percutaneous nephrolithotomy is the gold standard for treatment of renal stones larger than 20 mm in diameter. The outcomes PCNL are highly dependent on accuracy puncture step, order to achieve a suitable access and reach stone with precise direct path. Thus, performing puncturing get most crucial challenging step procedure steepest learning curve. Many simulation methods systems have been developed help trainees requested competency level access. Simulators include human cadavers, animal...
The paper describes an estimation and identification procedure that allows to reconstruct the inertial parameters of a rigid load attached end-effector industrial manipulator. In particular, proposed method adopts multirate quaternion-based Kalman filter, fusing measurements obtained from robot kinematics sensors at possibly different sampling frequencies, estimate linear accelerations angular velocities/accelerations load. Then, recursive total least-squares (RTLS) process is executed...
In order to improve the safety, reliability, efficiency, and sustainability of offshore wind turbine installations, thus avoiding expensive unplanned maintenance, accommodation faults in their earlier occurrence is fundamental. Therefore, main contribution this work consists development a fault scheme applied control nonlinear model. particular, data-driven strategy relying on fuzzy models exploited build tolerant scheme. Fuzzy theory here since it allows approximate easily unknown model...
The installed wind power capacity is growing worldwide. Remote condition monitoring of turbines employed to achieve higher up-times and lower maintenance costs. Machine learning approaches can be used for detecting developing faults in their earlier occurrence. However, training fault detection models may require large amounts past present data. These data are often not available or representative the current operation behaviour. acquired with supervisory control acquisition systems. Note...
Despite the resolution of pathology at admission, many hospitalized patients are discharged in a worse functional state, particularly terms walking capabilities, due to hospitalization inactivity. Early interventions maintain state through exercise such as passive mobilization, executed during hospitalization, have been proven be effective preventing physical and cognitive decline. Unfortunately, can excluded from treatments high number people limited availability healthcare personnel. This...
In order to improve the availability of offshore wind farms, thus avoiding unplanned operation and maintenance costs, which can be high for installations, accommodation faults in their earlier occurrence is fundamental. Therefore, this paper addresses design an active fault tolerant control scheme that applied a small park benchmark nine turbines, based on nonlinear models, as well interactions among turbines farm. The controller relies on-line estimate signals generated by filters designed...
In order to improve the safety, reliability, and efficiency of offshore wind park installations, thus avoiding expensive unplanned maintenance, accommodation faults in their earlier occurrence is fundamental. Therefore, main contribution this paper consists development a fault tolerant control scheme by means viable approach. particular, data-driven strategy based on fuzzy logic exploited for deriving model required controller. Fuzzy theory here since it able approximate easily unknown...