1,721,105 research outputs found
The role of Industry 4.0 enabling technologies for safety management: A systematic literature review
Full text linkInnovations introduced during the Industry 4.0 era consist in the integration of the so called "nine pillars of technologies" in manufacturing, transforming the conventional factory in a smart factory. The aim of this study is to investigate enabling technologies of Industry 4.0, focusing on technologies that have a greater impact on safety management. Main characteristics of such technologies will be identified and described according to their use in an industrial environment. In order to do this, we chose a systematic literature review (SLR) to answer the research question in a comprehensively way. Results show that articles can be grouped according to different criteria. Moreover, we found that Industry 4.0 can increase safety levels in warehouse and logistic, as well as several solutions are available for building sector
An integrated and parametric simulation model to improve production and maintenance processes: Towards a digital factory performance
No full textIn recent years with the emergence of the concept of Industry 4.0 digitalization is transforming the industrial scenario. A great attention is focused on integrated simulation system, an emerging enabling technology, as a particular decision support tool, to represent the increasingly complex modern production systems. The advantage is that it is possible to perform simulations and reconfigure models to evaluate modified or alternative scenarios to achieve current demands of increasingly competitive markets. The aim of the present research is the definition of an integrated parametric simulation model for integration management enhancing the production and maintenance process. Thus, a framework for implementing simulation models that help production and maintenance managers to make cost-effective decisions as well as optimize the use of resources is developed. System Dynamics approach is used to simulate, through PowerSim Software®, the nonlinear behavior of the analyzed complex systems over time. The results revealed that the proposed simulation optimization procedure can be used to solve and to manage complexity in a ‘‘real-time’’. Furthermore, the output of this simulation optimization procedure gives the decision maker the most probable scenario
Macroblock Skipping Algorithms for High Definition H.264/AVC Video Coding in the Baseline Profile
No full textComparison of Machine Learning approaches for Stress Detection from Wearable Sensors Data
No full textStress is a prevalent and growing phenomenon in the modern world potentially leading to significant repercussions on both physical and mental health. The analysis of physiological signals, collected from wearable sensors, has emerged as a promising approach to predicting and managing stress. Methods based on machine learning techniques have been defined in the literature and achieved promising results by using handcrafted features extracted from the signal. However, there is no consensus on the list of features, while deep learning approaches that overcomes the problem require significant computational power and a large amount of data. In this paper, we present a comprehensive view of the most common representative machine learning algorithms applied to the stress detection domain by giving a reference point for both academia and industry professionals in this application field. This study considers fragments of signals without extracting any features and uses a public dataset, WESAD, that contains high-resolution physiological, including blood volume pulse, electrocardiogram and electromyogram. The data collected from 15 subjects during a lab study are heterogeneous and characterized by different frequencies and noises due to some devices. After preprocessing, we assess the performance of ten machine learning algorithms belonging to four models (tree, ensemble, linear and neighbours) on the WESAD by facing the problem as binary (stress/no-stress) and multiclass (baseline, stress, and amusement) classifications. Our results, evaluated in terms of classical metrics, show that Random Forest outperforms the others in binary and multi-class approaches
AHP-TOPSIS model to evaluate maintenance strategy using RAMS and production parameters
No full textThe focus of the present research concerns a maintenance strategy selection model. An integrated approach is proposed, able to match Analytic Hierarchy Process (AHP) with Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) for the evaluation of maintenance policy, in order to improve production performance and to reduce cost organization. The proposed model has been applied in a real case study of a textile industry. Different maintenance alternatives were considered and different criteria and sub-criteria were evaluated using Reliability, Availability, Maintainability, Safety (RAMS) and production parameters. The results suggest the best maintenance solution for all machines in the analyzed textile process. The model has also been tested, by performing a sensitivity analysis, where the weight of each criterion has been varied. The proposed technique is based on general parameters and for this reason can be used in different industrial fields to select proper maintenance strategies. The results and the satisfaction of management derived by using the proposed method confirms how AHP-TOPSIS methodology represents an effective approach to arrive at best maintenance selection in order to reduce Maintenance Cost and increase System Availability
- …
