Showing papers by "David Romero published in 2022"

The Triple Bottom Line of Smart Manufacturing Technologies

Abstract: Smart manufacturing, Industry 4.0, and digital transformation are reshaping the manufacturing sector on a global scale. These initiatives are predominantly technology-driven and are enabled and supported by so-called smart technologies. In this chapter, we take on a sustainability perspective to understand the impact of smart manufacturing technologies on the triple bottom line (TBL). First, we derive and identify ten smart manufacturing technology clusters from recent literature. Second, we discuss each with a focus on the three TBL dimensions, namely: economic, environmental, and social bottom lines. Third, we discuss the challenges and barriers that hinder widespread adoption of the identified technology clusters. We conclude the chapter with a bold outlook for the future development of and the many opportunities offered by smart manufacturing technologies with regard to sustainable manufacturing operations.

Phonotactic Language Recognition Using A Universal Phoneme Recognizer and A Transformer Architecture

Abstract: In this paper, we describe a phonotactic language recognition model that effectively manages long and short n-gram input sequences to learn contextual phonotactic-based vector embeddings. Our approach uses a transformer-based encoder that integrates a sliding window attention to attempt finding discriminative short and long cooccurrences of language dependent n-gram phonetic units. We then evaluate and compare the use of different phoneme recognizers (Brno and Allosaurus) and sub-unit tokenizers to help select the more discriminative n-grams. The proposed architecture is evaluated using the Kalaka-3 database that contains clean and noisy audio recordings for very similar languages (i.e. Iberian languages, e.g., Spanish, Galician, Catalan). We provide results using the Cavg and accuracy metrics used in NIST evaluations. The experimental results show that our proposed approach outperforms by 21% of relative improvement to the best system presented in the Albayzin LR competition.

Workforce Learning Curves for Human-Based Assembly Operations: A State-of-the-Art Review

Abstract: In this state-of-the-art review, the authors explore the recent advancements in the topics of learning curve models and their estimation methods for manual operations and processes as well as the data collection and monitoring technologies used for supporting these. This objective is achieved by answering the following three research questions: (RQ1) What calculation methods for estimating the learning curve of a worker exist in the recent scientific literature? (RQ2) What other usages are manufacturing enterprises giving to the modern learning curve prediction models according to the recent scientific literature? and (RQ3) What data collection and monitoring technologies exist to automatically acquire the data needed to create and continuously update the learning curve of an assembly operator? To do so, the PRISMA methodology for literature reviews was used, only including journal articles and conference papers referencing the topic of manual operations and processes, and to fulfil the criteria of a state-of-the-art review, only the literary corpus generated in the last five years (from 2017 to 2022) was reviewed. The scientific databases where the explorative research was carried out were Scopus and Web of Science. Such research resulted in 11 relevant journal articles and international conference papers, which were first reviewed, synthesized, and then compared. Four estimating methods were found for learning curves, and one recently developed learning curve model was found. As for the data collection and monitoring technologies, six frameworks were found and reviewed. Lastly, in the discussion, different areas of opportunity were found in the current state-of-the-art, mainly by combining the existing learning curve models and their estimation methods and feeding these with modern real-time data collection and monitoring frameworks.

Thematic Research Framework for Eco-Efficient and Circular Industrial Systems

Abstract: AbstractGlobal sustainability challenges are increasingly constraining and driving industrial development. Eco-efficiency and circular economy are powerful concepts providing guiding principles to achieve superior environmental performance. However, they are not systematically integrated into the design, planning, development, management and improvement of industrial systems, potentially resulting in increased environmental impacts and other unintended consequences. This paper presents a thematic research framework based on workshops with manufacturers and researchers in the field of production engineering and management. The framework aims to establish a stronger foundation to advance research and technological development for eco-efficient and circular industrial systems, embracing environmental sustainability as core operating principles.KeywordsCircular economyEco-efficiencyGreen manufacturingSustainable productionResearch framework