- Structural Health Monitoring Techniques
- Concrete Corrosion and Durability
- Infrastructure Maintenance and Monitoring
- Fault Detection and Control Systems
- Machine Fault Diagnosis Techniques
- Mineral Processing and Grinding
- Advanced machining processes and optimization
- Ultrasonics and Acoustic Wave Propagation
- Belt Conveyor Systems Engineering
- Hydraulic and Pneumatic Systems
- Advanced Fiber Optic Sensors
- Gear and Bearing Dynamics Analysis
- Advanced Data Processing Techniques
- Dam Engineering and Safety
- Scheduling and Optimization Algorithms
- Non-Destructive Testing Techniques
- Model Reduction and Neural Networks
- Vibration and Dynamic Analysis
- Smart Materials for Construction
- Industrial Vision Systems and Defect Detection
- Real-time simulation and control systems
- Flexible and Reconfigurable Manufacturing Systems
- Engineering Diagnostics and Reliability
- Structural Engineering and Vibration Analysis
- Wind and Air Flow Studies
Politecnico di Milano
2021-2025
This paper introduces a framework to perform operational modal analysis (OMA) for structural health monitoring (SHM) by presenting the development and validation of low-power, solar-powered wireless sensor network (WSN) tailored bridge structures. The system integrates accelerometers temperature sensors dynamic assessment, all interconnected through energy-efficient message queuing telemetry transport (MQTT) messaging protocol. Moreover, it delves into details selection, calibration, design...
When addressing product quality standards in manufacturing lines, a critical issue is the identification of parameters that define final and their tracking. The problem process control under inconsistent working condition an automatic machinery, i.e. when some are highly variable, still quite unexplored literature. This objective becomes even more challenging most important variables not directly measurable. paper demonstrates it possible to achieve by coupling soft sensor, whose predictive...
In industrial settings, machinery components inevitably wear and degrade due to friction between moving parts. To address this, various maintenance strategies, including corrective, preventive, predictive maintenance, are commonly employed. This paper focuses on through vibration analysis, utilizing data-driven models. study explores the application of unsupervised learning methods, particularly Convolutional Autoencoders (CAEs) variational (VAEs), for anomaly detection (AD) in signals. By...
Structural health monitoring of civil infrastructure, such as bridges and buildings, has become a trending topic in the last few years. The key factor is technological push given by new technologies that permit acquisition, storage, processing visualisation data real time, thus assessing structure’s condition. However, related to anomaly conditions are difficult retrieve, and, time those met, general, it too late. For this reason, problem becomes unsupervised, since no labelled available,...
The application of intelligent systems for structural health monitoring is investigated. A change in the nominal configuration can be related to a defect that has monitored before it reaches critical condition. Evidently, ability automatically detect changes structure very attractive feature. When there no prior knowledge on system, deep learning models could effectively and enhance capability determining damage location. However, acquisition data damaged structures not always practical. In...
Abstract In the framework of direct Structural Health Monitoring approaches, this paper presents a low frequency range analysis performed on steel truss bridge designed in 1946 and built up Northern Italy. The is instrumented with permanent structural health monitoring system, that guarantees continuous flux data information from heterogeneous set sensors. analysis, static quasistatic responses are considered. These experimental merged analogous outputs obtained numerical simulations, FE...
Bridges and viaducts worldwide are threatened by ageing, increasing loads climate-related extreme events. The situation calls for immediate actions to prevent catastrophic failures extend the life of our infrastructural heritage. In this regard, thanks significant efforts from academics, Structural Health Monitoring is paving its way towards application in real world. Unlike simple monitoring activity, which not new field, SHM more identifiable as a paradigm, encompassing several steps...
This paper presents a deep learning approach for detecting early fault in bearings. The identification of bearings defects represents an important problem the field rotating machines. Sudden failures may occur, leading to breakdown machinery. For this reason, prediction possible faults has become major issue study bearing elements. Different diagnosis techniques have been developed during years based on aggregated parameters (i.e. features) that are computed starting from time domain,...
In modern manufacturing industries, quality control systems are crucial components that rising attention in production environments; companies looking for new and innovative ways to identify minimize the quantity of non-compliant products. Intelligent is particularly important when evaluating outcome a line complex task (for example visual inspection not sufficient). The first step building smart process system identification all variables related final condition product. If key-variables...
Due to an increasing number of bridges approaching the end their design lives, there is a growing interest by infrastructure managers on monitoring systems able provide information service capability structures. Focusing, in particular, railway bridges, serviceability related both structural and runnability, where first bridge, while second constraints rail geometry. In this work authors present investigation permanent system detect presence damages that would lead exceedance threshold...
Since 2019 researchers in the field of deep learning have been exploring possibilities Physics Informed Neural Networks (PINN). The training regular neural networks (NNs) involved an optimization where loss function depends exclusively on dataset available. In PINN this takes into account also physics problem, if it is known and governing equations are given. This paper explores advantages use PINNs with respect to NNs, privileged case a multibody model However, there still uncertainty...
The estimation of trains weight could be useful under certain circumstances. For instance, in the field structural health monitoring, some considerations can derived from evaluation load spectrum that an infrastructure has to withstand its lifetime. One approach estimate train is based on use strain gauges mounted rail. procedure allows associate local deformations with axle. However, present several limitations: they are regarded as delicate sensors, and their replacement burdensome...
In industrial automation, the transportation of unit loads plays a crucial role. This paper addresses under-explored area plastic chain conveyors, versatile and efficient means transport within production processes. Despite their widespread use, these conveyors suffer from wear tear due to continuous contact between guide rails, leading often tounscheduled shutdowns consequently increasing costs. The literature on monitoring solutions for such systems is sparse, particularly chains. bridges...
This paper introduces a framework to perform Operational Modal Analysis (OMA) for Structural Health Monitoring (SHM) by presenting the development and validation of low-power, solar-powered Wireless Sensor Network (WSN) tailored bridge structures. The system integrates accelerometers temperature sensors dynamic structural assessment, all interconnected through energy efficient MQTT (Message Queuing Telemetry Transport) messaging protocol. delves into details sensor selection, calibration,...
Vibration analysis is recognized as a powerful tool for fault diagnosis and quality control of industrial machineries. Accelerometer signals can provide measure the majority causes inaccuracy in manufacturing processes components' faults, which turn affect product quality. This paper provides identification method based on time frequency domain analysis. applied to an automatic press machine soft thermoplastic polymers. Pilot experiments conducted laboratory conditions allowed select proper...
In the field of structural health monitoring, adoption intelligent systems able to automatically detect changes in a structure are evidently attractive. A change baseline configuration can be an early predictor defect that has monitored before it reaches critical conditions. When there is no prior knowledge on system, deep learning models such as autoencoders could effectively and enhance capability determine damage location. this paper approach applied test rig consisting small building...
In recent years, real-time monitoring of health conditions for massive structures, such as bridges and buildings, has grown in interest. Some the key factors are possibility to estimate continuously condition, well a reduction personnel involved visual inspections operative costs. However, while dealing with it is extremely rare observe anomaly conditions, when those met general too late. Consequently, structural problem must be tackled an unsupervised one. The idea exploited this research...
Infrastructures are essential for the development and flourishing of countries; in this context, bridges play an irreplaceable role as links goods people. Nowadays, their structural integrity is threatened by ageing increased traffic loads: according to American Society Civil Engineering, 42% US at least 50 years old. The extension problem requires application techniques resource prioritization effective interventions. Structural health monitoring (SHM) has emerged a promising quantitative...