Additive manufacturing: studio delle non conformità geometriche e dimensionali in componenti realizzati mediante tecnica fused deposition modelling

La fabbricazione additiva è una classe di metodi di fabbricazione in cui il componente viene costruito aggiungendo strati di materiale l’uno sull’altro, sino alla completa realizzazione dello stesso. Si tratta di un principio di fabbricazione sostanzialmente differente da quelli tradizionali attualmente utilizzati, che si avvalgono di utensili per sottrarre materiale da un semilavorato, sino a conferire all’oggetto la forma desiderata, mentre i processi additivi non richiedono l’utilizzo di utensili. Il termine più comunemente utilizzato per la fabbricazione additiva è prototipazione rapida. Il termine “prototipazione”’ viene utilizzato in quanto i processi additivi sono stati utilizzati inizialmente solo per la produzione di prototipi, tuttavia con l’evoluzione delle tecnologie additive questi processi sono sempre più in grado di realizzare componenti di elevata complessità risultando competitivi anche per volumi di produzione medio-alti. Il termine “rapida” viene invece utilizzato in quanto i processi additivi vengono eseguiti molto più velocemente rispetto ai processi di produzione convenzionali. La fabbricazione additiva offre diversi vantaggi dal punto di vista di: • velocità: questi processi “rapidi” hanno brevi tempi di fabbricazione. • realizzazione di parti complesse: con i processi additivi, la complessità del componente ha uno scarso effetto sui tempi di costruzione, contrariamente a quanto avviene nei processi tradizionali dove la realizzazione di parti complesse può richiedere anche settimane. • materiali: la fabbricazione additiva è caratterizzata dalla vasta gamma di materiali che può utilizzare per la costruzione di pezzi. Inoltre, in alcuni processi si possono costruire pezzi le cui parti sono di materiali diversi. • produzioni a basso volume: molti processi tradizionali non sono convenienti per le produzioni a basso volume a causa degli alti costi iniziali dovuti alla lavorazione con utensili e tempi di setup lunghi.

Deep Learning Architectures for time of arrival detection in Acoustic Emissions Monitoring

Acoustic Emission (AE) monitoring can be used to detect the presence of damage as well as determine its location in Structural Health Monitoring (SHM) applications. Information on the time difference of the signal generated by the damage event arriving at different sensors is essential in performing localization. This makes the time of arrival (ToA) an important piece of information to retrieve from the AE signal. Generally, this is determined using statistical methods such as the Akaike Information Criterion (AIC) which is particularly prone to errors in the presence of noise. And given that the structures of interest are surrounded with harsh environments, a way to accurately estimate the arrival time in such noisy scenarios is of particular interest. In this work, two new methods are presented to estimate the arrival times of AE signals which are based on Machine Learning. Inspired by great results in the field, two models are presented which are Deep Learning models - a subset of machine learning. They are based on Convolutional Neural Network (CNN) and Capsule Neural Network (CapsNet). The primary advantage of such models is that they do not require the user to pre-define selected features but only require raw data to be given and the models establish non-linear relationships between the inputs and outputs. The performance of the models is evaluated using AE signals generated by a custom ray-tracing algorithm by propagating them on an aluminium plate and compared to AIC. It was found that the relative error in estimation on the test set was < 5% for the models compared to around 45% of AIC. The testing process was further continued by preparing an experimental setup and acquiring real AE signals to test on. Similar performances were observed where the two models not only outperform AIC by more than a magnitude in their average errors but also they were shown to be a lot more robust as compared to AIC which fails in the presence of noise.

Computer vision in aseptic pharmaceutical manufacturing: a deep learning-based approach to vial inspection and pack formation during a lyophilizer loading cycle

Vision systems are powerful tools playing an increasingly important role in modern industry, to detect errors and maintain product standards. With the enlarged availability of affordable industrial cameras, computer vision algorithms have been increasingly applied in industrial manufacturing processes monitoring. Until a few years ago, industrial computer vision applications relied only on ad-hoc algorithms designed for the specific object and acquisition setup being monitored, with a strong focus on co-designing the acquisition and processing pipeline. Deep learning has overcome these limits providing greater flexibility and faster re-configuration. In this work, the process to be inspected consists in vials’ pack formation entering a freeze-dryer, which is a common scenario in pharmaceutical active ingredient packaging lines. To ensure that the machine produces proper packs, a vision system is installed at the entrance of the freeze-dryer to detect eventual anomalies with execution times compatible with the production specifications. Other constraints come from sterility and safety standards required in pharmaceutical manufacturing. This work presents an overview about the production line, with particular focus on the vision system designed, and about all trials conducted to obtain the final performance. Transfer learning, alleviating the requirement for a large number of training data, combined with data augmentation methods, consisting in the generation of synthetic images, were used to effectively increase the performances while reducing the cost of data acquisition and annotation. The proposed vision algorithm is composed by two main subtasks, designed respectively to vials counting and discrepancy detection. The first one was trained on more than 23k vials (about 300 images) and tested on 5k more (about 75 images), whereas 60 training images and 52 testing images were used for the second one.

Mitigating non-Lambertian surfaces issues in Stereo Matching with Neural Radiance Fields

Depth estimation from images has long been regarded as a preferable alternative compared to expensive and intrusive active sensors, such as LiDAR and ToF. The topic has attracted the attention of an increasingly wide audience thanks to the great amount of application domains, such as autonomous driving, robotic navigation and 3D reconstruction. Among the various techniques employed for depth estimation, stereo matching is one of the most widespread, owing to its robustness, speed and simplicity in setup. Recent developments has been aided by the abundance of annotated stereo images, which granted to deep learning the opportunity to thrive in a research area where deep networks can reach state-of-the-art sub-pixel precision in most cases. Despite the recent findings, stereo matching still begets many open challenges, two among them being finding pixel correspondences in presence of objects that exhibits a non-Lambertian behaviour and processing high-resolution images. Recently, a novel dataset named Booster, which contains high-resolution stereo pairs featuring a large collection of labeled non-Lambertian objects, has been released. The work shown that training state-of-the-art deep neural network on such data improves the generalization capabilities of these networks also in presence of non-Lambertian surfaces. Regardless being a further step to tackle the aforementioned challenge, Booster includes a rather small number of annotated images, and thus cannot satisfy the intensive training requirements of deep learning. This thesis work aims to investigate novel view synthesis techniques to augment the Booster dataset, with ultimate goal of improving stereo matching reliability in presence of high-resolution images that displays non-Lambertian surfaces.

Conditional entropy and predictability for non-reversible Markov systems

The purpose of this thesis is to clarify the role of non-equilibrium stationary currents of Markov processes in the context of the predictability of future states of the system. Once the connection between the predictability and the conditional entropy is established, we provide a comprehensive approach to the definition of a multi-particle Markov system. In particular, starting from the well-known theory of random walk on network, we derive the non-linear master equation for an interacting multi-particle system under the one-step process hypothesis, highlighting the limits of its tractability and the prop- erties of its stationary solution. Lastly, in order to study the impact of the NESS on the predictability at short times, we analyze the conditional entropy by modulating the intensity of the stationary currents, both for a single-particle and a multi-particle Markov system. The results obtained analytically are numerically tested on a 5-node cycle network and put in correspondence with the stationary entropy production. Furthermore, because of the low dimensionality of the single-particle system, an analysis of its spectral properties as a function of the modulated stationary currents is performed.

Spatial-temporal variability of the benthic communities in Ravenna harbour using Autonomous Reef Monitoring Structures (ARMS) with focus on Non-Indigenous Species (NIS)

A Non-Indigenous Species (NIS) is defined as an organism, introduced outside its natural past or present range of distribution by humans, that successfully survives, reproduces, and establish in the new environment. Harbors and tourist marinas are considered NIS hotspots, as they are departure and arrival points for numerous vessels and because of the presence of free artificial substrates, which facilitate colonization by NIS. To early detect the arrival of new NIS, monitoring benthic communities in ports is essential. Autonomous Reef Monitoring Structures (ARMS) are standardized passive collectors that are used to assess marine benthic communities. Here we use an integrative approach based on multiple 3-month ARMS deployment (from April 2021 to October 2022) to characterize the benthic communities (with a focus on NIS) of two sites: a commercial port (Harbor) and a touristic Marina (Marina) of Ravenna. The colonizing sessile communities were assessed using percentage coverage of the taxa trough image analyses and vagile fauna (> 2 mm) was identified morphologically using a stereomicroscope and light microscope. Overall, 97 taxa were identified and 19 of them were NIS. All NIS were already observed in port environments in the Mediterranean Sea, but for the first time the presence of the polychaete Schistomeringos cf. japonica (Annenkova, 1937) was observed; however molecular analysis is needed to confirm its identity. Harbor and Marina host significantly different benthic communities, with significantly different abundance depending on the sampling period. While the differences between sites are related to their different environmental characteristic and their anthropogenic pressures, differences among times seems related to the different life cycle of the main abundant species. This thesis evidenced that ARMS, together with integrative taxonomic approaches, represent useful tools to early detect NIS and could be used for a long-term monitoring of their presence.