A5043391732- Fault Detection and Control Systems
- Real-time simulation and control systems
- Industrial Vision Systems and Defect Detection
- Advanced Control Systems Optimization
- Vehicle Dynamics and Control Systems
- Adaptive optics and wavefront sensing
- Building Energy and Comfort Optimization
- Advanced optical system design
- Control Systems and Identification
- Anomaly Detection Techniques and Applications
- Geophysics and Sensor Technology
- Advanced Statistical Process Monitoring
- Heat Transfer and Optimization
- Aerospace and Aviation Technology
- Optical measurement and interference techniques
- Refrigeration and Air Conditioning Technologies
- Iterative Learning Control Systems
- Advanced Frequency and Time Standards
- Advanced Fiber Laser Technologies
- Extremum Seeking Control Systems
- Magnetic confinement fusion research
- Image Processing Techniques and Applications
- Mechanical Engineering and Vibrations Research
- Access Control and Trust
- Smart Grid Energy Management
University of Padua
2015-2024
Conference Board
2022-2023
Inspire
2022
Electrolux (Italy)
2018
Istituto Nazionale di Fisica Nucleare, Sezione di Padova
2008-2017
Istituto Nazionale di Fisica Nucleare
2016
In this paper a multiple classifier machine learning methodology for Predictive Maintenance (PdM) is presented.PdM prominent strategy dealing with maintenance issues given the increasing need to minimize downtime and associated costs.One of challenges PdM generating so called 'health factors' or quantitative indicators status system issue, determining their relationship operating costs failure risk.The proposed allows dynamical decision rules be adopted management can used high-dimensional...
Silicon epitaxial deposition is a process strongly influenced by wafer temperature behavior, which has to be constantly monitored avoid the production of defective wafers. However, measurements are not reliable, and sensors have appropriately calibrated with some dedicated procedure. A predictive maintenance (PdM) system proposed aim predicting behavior scheduling control actions on in advance. Two different prediction techniques been employed compared: Kalman predictor particle filter...
Exploiting the huge amount of data collected by industries is definitely one main challenges so-called Big Data era. In this sense, Machine Learning has gained growing attention in scientific community, as it allows to extract valuable information means statistical predictive models trained on historical process data. Semiconductor Manufacturing, most extensively employed data-driven applications Virtual Metrology, where a costly or unmeasurable variable estimated cheap and easy obtain...
In the past recent years, Machine Learning methodologies have been applied in countless application areas. particular, they play a key role enabling Industry 4.0. However, one of main obstacles to diffusion Learning-based applications is related lack interpretability most these methods. this work, we propose an approach for defining `feature importance' Anomaly Detection problems. important task that has enormous applicability industrial scenarios. Indeed, it extremely relevant purpose...
Smart production monitoring is a crucial activity in advanced manufacturing for quality, control and maintenance purposes. Advanced Monitoring Systems aim to detect anomalies trends; are data patterns that have different characteristics from normal instances, while trends tendencies of move particular direction over time. In this work, we compare state-of-the-art ML approaches (ABOD, LOF, onlinePCA osPCA) outliers events high-dimensional problems. The compared anomaly detection strategies...
In this paper we introduce MATMPC, an open source software built in MATLAB for nonlinear model predictive control (NMPC). It is designed to facilitate modelling, controller design and simulation a wide class of NMPC applications. MATMPC has number algorithmic modules, including automatic differentiation, direct multiple shooting, condensing, linear quadratic program (QP) solver globalization. also supports unique Curvature-like Measure Nonlinearity (CMoN) MPC algorithm. been provide...
Advanced Monitoring Systems are fundamental in advanced manufacturing for control, quality and maintenance purposes. Nowadays, with the increasing availability of data production equipment, need high-dimensional Anomaly Detection techniques is thriving; anomalies patterns that have different characteristics from normal instances may be associated faults or drifts production. Tools dealing monitoring problems provided by Machine Learning: this paper, we test performance a state-of-the-art...
The rise of industry 4.0 and data-intensive manufacturing makes advanced process control (APC) applications more relevant than ever for process/production optimization, related costs reduction, increased efficiency. One the most important APC technologies is virtual metrology (VM). VM aims at exploiting information already available in process/system under exam, to estimate quantities that are costly or impossible measure. Machine learning (ML) approaches foremost choice design solutions. A...
In manufacturing industries, it is of fundamental importance to detect anomalies in production order meet the required quality goals and limit number defective products that are accidentally delivered customers. Nevertheless, monitoring systems currently employed typically very simple rely on a set univariate control charts fail capture multivariate complex nature real-world industrial systems. such context, Machine Learning (ML)-based approaches for Anomaly Detection (AD) have proven be...
The problem of plasma boundary reconstruction in relation to shape control was discussed. different approaches guaranteeing accuracy and robustness were presented. Deformable models provide a new formulation the as continuous contour, which facilitates more accurate estimation global parameters, able describe evolution realistic way. results analyses performed on JET ITER support validity snake methodology.
Driving simulators play an important role in the development of new vehicles and advanced driver assistance devices. In fact, on one hand, having a human driving simulator allows automotive OEMs to bridge gap between virtual prototyping on-road testing during vehicle phase. On other novel systems (such as accident avoidance systems) can be safely tested by operating virtual, highly realistic environment, while being exposed hazardous situations. both applications, it is crucial faithfully...
Driving simulators are widely used in many different applications, such as driver training, vehicle development, and medical studies. To fully exploit the potential of devices, it is crucial to develop platform motion control strategies that generate realistic driving feelings. This has be achieved while keeping within its limited operation space. Such go under name cueing algorithms. In this paper a particular implementation Motion Cueing algorithm described, based on Model Predictive...
In this paper an approach to deal with Predictive Maintenance (PdM) problems time-series data is discussed. PdM a important tackle maintenance and it gaining increasing attention in advanced manufacturing minimize scrap materials, downtime, associated costs. approaches are generally based on Machine Learning tools that require the availability of historical process data. Given exponential growth logging modern equipment, time series dataset increasingly available applications. To exploit for...
The use of dynamical driving simulators is nowadays common in many different application fields, such as driver training, vehicle development, and medical studies. Platforms with mechanical structures have been designed, depending on the particular corresponding targeted market. effectiveness devices related to their capabilities well reproducing sensations, hence, it crucial that motion control strategies generate both realistic feasible inputs platform, ensure kept within its limited...