In modern industrial systems, diagnosing faults in time and using the best methods becomes more and more crucial. It is possible to fail a system or to waste resources if faults are not detected or are detected late. Machine learning and deep learning have proposed various methods for data-based fault diagnosis, and we are looking for the most reliable and practical ones. This paper aims to develop a framework based on deep learning and reinforcement learning for fault detection. We can increase accuracy, overcome data imbalance, and better predict future defects by updating the reinforcement learning policy when new data is received. By implementing this method, we will see an increase of $3\%$ in all evaluation metrics, an improvement in prediction speed, and $3\%$ - $4\%$ in all evaluation metrics compared to typical backpropagation multi-layer neural network prediction with similar parameters.

In this context, additive manufacturing (AM), and specifically metal additive manufacturing (MAM), is particularly suited to industrial paradigms based on automation, flexibility, and efficiency. Indeed, MAM can be considered as a native digital technology, providing a seamless workflow from the digital design environment to the final product, which can be potentially completed without any human intervention [30]. However, a broader adoption of MAM technologies in industry is still hindered by such factors as: (i) lack of widely adopted standardisations and specifications of material properties, machines, and processes [40]; (ii) lack of adequate digital infrastructures, and interoperability issues between different production environments [7]; (iii) lack of accessible interfaces providing process information that is easily interpretable by non-experts [47]; (iv) lack of advanced control systems capable of automatically adjusting, at run-time, the production parameters [54]; (v) challenges in quality assurance due part accuracy and variability [48]. Thus, achieving semantically transparent and interoperable data sets and systems, to address Points (i), (ii) and (iii) above, is arguably of paramount importance. In this direction, several approaches based on ontology engineering and knowledge representation techniques have been proposed [29, 10, 66, 67, 60]. Broadly conceived as formal specifications of conceptualisations over a domain of interest, computational ontologies (cf.

Drones working together can create large 3D-printed structures made of foam or cement. The experiments are paving the way for a future where swarms of drones could help construct extremely tall or intricate buildings and other structures like bridges without the need for support scaffolding or large construction machinery. "We're talking about being able to build something of limitless size, theoretically speaking," says Robert Stuart-Smith at the University of Pennsylvania. Such creations would only be restricted by structural engineering constraints and factors like drone flight logistics. The drone swarm construction takes inspiration from animals such as wasps and termites.

Example image of the 3D printer nozzle used by the machine learning algorithm to detect and correct errors in real time. Engineers from the University of Cambridge have developed a machine learning algorithm that can detect and correct a wide variety of different errors in real time, and can be easily added to new or existing machines to enhance their capabilities. Details of their low-cost approach are reported in the journal Nature Communications. However, it is also vulnerable to production errors, from small-scale inaccuracies and mechanical weaknesses through to total build failures. Currently, the way to prevent or correct these errors is for a skilled worker to observe the process.

Machine Learning capable of upgrading FDM 3D printed parts to such a level that they overtake their injection moulded counterparts.

Nonlinear state estimation (SE), with the goal of estimating complex bus voltages based on all types of measurements available in the power system, is usually solved using the iterative Gauss-Newton method. The nonlinear SE presents some difficulties when considering inputs from both phasor measurement units and supervisory control and data acquisition system. These include numerical instabilities, convergence time depending on the starting point of the iterative method, and the quadratic computational complexity of a single iteration regarding the number of state variables. This paper introduces an original graph neural network based SE implementation over the augmented factor graph of the nonlinear power system SE, capable of incorporating measurements on both branches and buses, as well as both phasor and legacy measurements. The proposed regression model has linear computational complexity during the inference time once trained, with a possibility of distributed implementation. Since the method is noniterative and non-matrix-based, it is resilient to the problems that the Gauss-Newton solver is prone to. Aside from prediction accuracy on the test set, the proposed model demonstrates robustness when simulating cyber attacks and unobservable scenarios due to communication irregularities. In those cases, prediction errors are sustained locally, with no effect on the rest of the power system's results.

With the rapid development of powder-based additive manufacturing, depowdering, a process of removing unfused powder that covers 3D-printed parts, has become a major bottleneck to further improve its productiveness. Traditional manual depowdering is extremely time-consuming and costly, and some prior automated systems either require pre-depowdering or lack adaptability to different 3D-printed parts. To solve these problems, we introduce a robotic system that automatically removes unfused powder from the surface of 3D-printed parts. The key component is a visual perception system, which consists of a pose-tracking module that tracks the 6D pose of powder-occluded parts in real-time, and a progress estimation module that estimates the depowdering completion percentage. The tracking module can be run efficiently on a laptop CPU at up to 60 FPS. Experiments show that our depowdering system can remove unfused powder from the surface of various 3D-printed parts without causing any damage. To the best of our knowledge, this is one of the first vision-based robotic depowdering systems that adapt to parts with various shapes without the need for pre-depowdering.

A multilingual (English/Spanish) immersive learning environment is being created by an assistant professor at the University of Texas using virtual reality technology to help students better grasp the topic of additive manufacturing. The project, titled "Enhancing Active Learning in Additive Manufacturing Using a Bilingual, Assisted Virtual-Reality Platform," will be under the direction of Shuchisnigdha Deb, assistant professor in the Department of Industrial, Manufacturing, and Systems Engineering (IMSE). The research is being supported by a grant from the National Science Foundation worth $837,000. Emma Yang and Amanda Olsen, two other ISME faculty members from the College of Education's Department of Curriculum and Instruction, are also on the team. Deb asserted that teaching kids about additive manufacturing is crucial for the advancement of robots, augmented reality, and other technologies.

A research team led by Prof. Gao Ge and Jiang Li from the Hefei Institutes of Physical Science of the Chinese Academy of Sciences has investigated the fault diagnosis of a pulse width modulation converter and proposed a neural network fault diagnosis algorithm to solve existing problems in this field. Results were published in IEEE Transactions on Power Electronics. Pulse width modulation has the advantages of high efficiency, high power density and high reliability. But due to the complexity of the drive systems and the diversity of fusion joint operation, pulse-width modulating voltage source converter systems are prone to suffer critical failures. Therefore, research on fault diagnostic technology is of deep concern, especially open-circuit fault diagnosis, which was what scientists have been focusing in this study.

Scientists and engineers are constantly developing new materials with unique properties that can be used for 3D printing, but figuring out howto print with these materials can be a complex, costly conundrum. Often, an expert operator must use manual trial-and-error -- possibly making thousands of prints -- to determine ideal parameters that consistently print a new material effectively. These parameters include printing speed and how much material the printer deposits. MIT researchers have now used artificial intelligence to streamline this procedure. They developed a machine-learning system that uses computer vision to watch the manufacturing process and then correct errors in how it handles the material in real-time.