Tolerance optimization with statistical approach in the CAT environment

Nowadays, product development in all its phases plays a fundamental role in the industrial chain. The need for a company to compete at high levels, the need to be quick in responding to market demands and therefore to be able to engineer the product quickly and with a high level of quality, has led to the need to get involved in new more advanced methods/ processes. In recent years, we are moving away from the concept of 2D-based design and production and approaching the concept of Model Based Definition. By using this approach, increasingly complex systems turn out to be easier to deal with but above all cheaper in obtaining them. Thanks to the Model Based Definition it is possible to share data in a lean and simple way to the entire engineering and production chain of the product. The great advantage of this approach is precisely the uniqueness of the information. In this specific thesis work, this approach has been exploited in the context of tolerances with the aid of CAD / CAT software. Tolerance analysis or dimensional variation analysis is a way to understand how sources of variation in part size and assembly constraints propagate between parts and assemblies and how that range affects the ability of a project to meet its requirements. It is critically important to note how tolerance directly affects the cost and performance of products. Worst Case Analysis (WCA) and Statistical analysis (RSS) are the two principal methods in DVA. The thesis aims to show the advantages of using statistical dimensional analysis by creating and examining various case studies, using PTC CREO software for CAD modeling and CETOL 6σ for tolerance analysis. Moreover, it will be provided a comparison between manual and 3D analysis, focusing the attention to the information lost in the 1D case. The results obtained allow us to highlight the need to use this approach from the early stages of the product design cycle.

A maximum entropy approach to disturbed ecosystems

The current climate crisis requires a comprehensive understanding of biodiversity to acknowledge how ecosystems’ responses to anthropogenic disturbances may result in feedback that can either mitigate or exacerbate global warming. Although ecosystems are dynamic and macroecological patterns change drastically in response to disturbance, dynamic macroecology has received insufficient attention and theoretical formalisation. In this context, the maximum entropy principle (MaxEnt) could provide an effective inference procedure to study ecosystems. Since the improper usage of entropy outside its scope often leads to misconceptions, the opening chapter will clarify its meaning by following its evolution from classical thermodynamics to information theory. The second chapter introduces the study of ecosystems from a physicist’s viewpoint. In particular, the MaxEnt Theory of Ecology (METE) will be the cornerstone of the discussion. METE predicts the shapes of macroecological metrics in relatively static ecosystems using constraints imposed by static state variables. However, in disturbed ecosystems with macroscale state variables that change rapidly over time, its predictions tend to fail. In the final chapter, DynaMETE is therefore presented as an extension of METE from static to dynamic. By predicting how macroecological patterns are likely to change in response to perturbations, DynaMETE can contribute to a better understanding of disturbed ecosystems’ fate and the improvement of conservation and management of carbon sinks, like forests. Targeted strategies in ecosystem management are now indispensable to enhance the interdependence of human well-being and the health of ecosystems, thus avoiding climate change tipping points.

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.

Machine learning approach to the extended Hubbard model

The 1d extended Hubbard model with soft-shoulder potential has proved itself to be very difficult to study due its non solvability and to competition between terms of the Hamiltonian. Given this, we tried to investigate its phase diagram for filling n=2/5 and range of soft-shoulder potential r=2 by using Machine Learning techniques. That led to a rich phase diagram; calling U, V the parameters associated to the Hubbard potential and the soft-shoulder potential respectively, we found that for V<5 and U>3 the system is always in Tomonaga Luttinger Liquid phase, then becomes a Cluster Luttinger Liquid for 57, with a quasi-perfect crystal in the U<3V/2 and U>5 region. Finally we found that for U<5 and V>2-3 the system shall maintain the Cluster Luttinger Liquid structure, with a residual in-block single particle mobility.

Robotic Manipulation of DLOs for Wiring Harness Assembly: a Machine Learning Approach

In recent times, a significant research effort has been focused on how deformable linear objects (DLOs) can be manipulated for real world applications such as assembly of wiring harnesses for the automotive and aerospace sector. This represents an open topic because of the difficulties in modelling accurately the behaviour of these objects and simulate a task involving their manipulation, considering a variety of different scenarios. These problems have led to the development of data-driven techniques in which machine learning techniques are exploited to obtain reliable solutions. However, this approach makes the solution difficult to be extended, since the learning must be replicated almost from scratch as the scenario changes. It follows that some model-based methodology must be introduced to generalize the results and reduce the training effort accordingly. The objective of this thesis is to develop a solution for the DLOs manipulation to assemble a wiring harness for the automotive sector based on adaptation of a base trajectory set by means of reinforcement learning methods. The idea is to create a trajectory planning software capable of solving the proposed task, reducing where possible the learning time, which is done in real time, but at the same time presenting suitable performance and reliability. The solution has been implemented on a collaborative 7-DOFs Panda robot at the Laboratory of Automation and Robotics of the University of Bologna. Experimental results are reported showing how the robot is capable of optimizing the manipulation of the DLOs gaining experience along the task repetition, but showing at the same time a high success rate from the very beginning of the learning phase.

Machine Learning in Automatic Tabulation for Constraint Model Reformulation

Combinatorial decision and optimization problems belong to numerous applications, such as logistics and scheduling, and can be solved with various approaches. Boolean Satisfiability and Constraint Programming solvers are some of the most used ones and their performance is significantly influenced by the model chosen to represent a given problem. This has led to the study of model reformulation methods, one of which is tabulation, that consists in rewriting the expression of a constraint in terms of a table constraint. To apply it, one should identify which constraints can help and which can hinder the solving process. So far this has been performed by hand, for example in MiniZinc, or automatically with manually designed heuristics, in Savile Row. Though, it has been shown that the performances of these heuristics differ across problems and solvers, in some cases helping and in others hindering the solving procedure. However, recent works in the field of combinatorial optimization have shown that Machine Learning (ML) can be increasingly useful in the model reformulation steps. This thesis aims to design a ML approach to identify the instances for which Savile Row’s heuristics should be activated. Additionally, it is possible that the heuristics miss some good tabulation opportunities, so we perform an exploratory analysis for the creation of a ML classifier able to predict whether or not a constraint should be tabulated. The results reached towards the first goal show that a random forest classifier leads to an increase in the performances of 4 different solvers. The experimental results in the second task show that a ML approach could improve the performance of a solver for some problem classes.