Explore the vast range of titles available.

A major goal of materials design is to find material structures with desired properties and in a second step to find a processing path to reach one of these structures. In this paper, we propose and investigate a deep reinforcement learning approach for the optimization of processing paths. The goal is to find optimal processing paths in the material structure space that lead to target-structures, which have been identified beforehand to result in desired material properties. There exists a target set containing one or multiple different structures, bearing the desired properties. Our proposed methods can find an optimal path from a start structure to a single target structure, or optimize the processing paths to one of the equivalent target-structures in the set. In the latter case, the algorithm learns during processing to simultaneously identify the best reachable target structure and the optimal path to it. The proposed methods belong to the family of model-free deep reinforcement learning algorithms. They are guided by structure representations as features of the process state and by a reward signal, which is formulated based on a distance function in the structure space. Model-free reinforcement learning algorithms learn through trial and error while interacting with the process. Thereby, they are not restricted to information from a priori sampled processing data and are able to adapt to the specific process. The optimization itself is model-free and does not require any prior knowledge about the process itself. We instantiate and evaluate the proposed methods by optimizing paths of a generic metal forming process. We show the ability of both methods to find processing paths leading close to target structures and the ability of the extended method to identify target-structures that can be reached effectively and efficiently and to focus on these targets for sample efficient processing path optimization.

The second edition of this handbook provides a state-of-the-art overview on the various aspects in the rapidly developing field of robotics. Reaching for the human frontier, robotics is vigorously engaged in the growing challenges of new emerging domains.

Machine tools constitute the backbone of the industrial sector, representing the largest global inventory of equipment. The carbon emissions resulting from the production of each machine tool merit attention. Effective management of carbon emissions in the machine tool manufacturing process is crucial. This paper introduces a novel method for early carbon emission warnings in the machine tool manufacturing process, utilizing an adaptive dynamic exponentially weighted moving average (EWMA) approach. This method addresses the challenges in identifying and monitoring abnormal carbon emissions, emerging from uncertainties and dynamic correlations. Utilizing dynamic sampling techniques and adaptive principles, this method constructs an adaptive dynamic EWMA control chart. The EWMA control chart incorporates a multi-objective optimization design model, concentrating on carbon emissions in the machine tool manufacturing process, and incorporates statistical, economic, and environmental objectives. To mitigate slow convergence rates and enhance optimization accuracy in complex control chart multi-objective optimization algorithms, this study proposes an enhanced Harris hawks optimization (HHO) algorithm as the solving algorithm. Finally, the application of this method is demonstrated through the monitoring of carbon emissions in the manufacturing process of a five-axis machine tool (EOC), as a case study. The results validate the method’s rapid responsiveness to abnormal carbon emissions, providing alerts. This further confirms the efficacy and feasibility of the proposed approach. Ultimately, this approach offers a viable strategy for fostering environmentally conscious and high-quality growth in the machine tool industry.

This book provides in-depth theoretical and practical information on recent advances in micro-manufacturing technologies and processes, covering such topics as micro-injection moulding, micro-cutting, micro-EDM, micro-assembly, micro-additive manufacturing, moulded interconnected devices, and microscale metrology. It is designed to provide complementary material for the related e-learning platform on micro-manufacturing developed within the framework of the Leonardo da Vinci project 2013-3748/542424: MIMAN-T: Micro-Manufacturing Training System for SMEs. The book is mainly addressed to technicians and prospective professionals in the sector and will serve as an easily usable tool to facilitate the translation of micro-manufacturing technologies into tangible industrial benefits. Numerous examples are included to assist readers in learning and implementing the described technologies. In addition, an individual chapter is devoted to technological foresight, addressing market analysis and business models for micro-manufacturers.

This book provides background and guidance on the use of the structural hot-spot stress approach to fatigue analysis.

This book develops a comprehensive concept for energy performance management of machine tools, which guides the transition towards energy efficient machine tools using four innovative concept modules, which are embedded into a step-by-step workflow model.

Systems and Applications in Optical Fiber Sensor Technology The essential technology which underpins developments in optical fiber sensors continues to expand, and continues to be driven to a very large extent by advances in optoelectronics which have been produced for the ever-expanding optical com­ munications systems and networks of the world. The steps forward in the technol­ ogy, often accompanied by a reduction in the price of associated components, have been, and continue to be, adapted for use in a wide variety of optical fiber sensor systems. These include, for example, the use of photoinduced gratings as fiber sensor components, coupled with the wider availability of shorter wavelength lasers, bright luminescent sources and high-sensitivity detectors which have opened up new possibilities for both novel fiber optic sensor applications and new sensing systems. This is to be welcomed at a time when, coupled with integrated optic miniaturized devices and detectors, real possibilities of systems integration, at lower cost and increased utility, can be offered. The fiber laser, and the expansions of the types and availability of the doped fiber on which it is based, offer further examples of the integration of the essential components of advanced optical sensor systems, fitted for a new range of applications.

A substantial portion of this book is a revised version of Discrete Event Systems: Modeling and Performance Analysis (1993), which was written by the first author and received the 1999 Harold Chestnut Prize, awarded by the International Federation of Automatic Control (IFAC) for best control engineering textbook. This new expanded book is a comprehensive introduction to the field of discrete event systems, emphasizing breadth of coverage and accessibility of the material to readers with different backgrounds. Its key feature is the emphasis placed on a unified modeling framework that transcends specific application areas and allows linking of the following topics in a coherent manner: language and automata theory, supervisory control, Petri net theory, (max,+) algebra, Markov chains and queueing theory, discrete-event simulation, perturbation analysis, and concurrent estimation techniques. Introduction to Discrete Event Systems will be of interest to advanced-level students in a variety of disciplines where the study of discrete event systems is relevant: control, communications, computer engineering, computer science, manufacturing engineering, operations research, and industrial engineering.

High level academic ebook