The importance of industry 4.0 is increasing continuously in the apparel sector. The evolution in manufacturing with implementation of the new modes of production nowadays is widely known. The benefits that come from each new development in the digital information technology has to be fasten embraced. The main advantage is the improvements of the supply chain efficiency. The innovation based on the industry 4.0 allow companies to optimize their actual production systems and enhance more efficient processes. Smart manufacturing can help the apparel industry more specifically by making the concept of affordable mass customization in reality. This paper helps us understand how industry 4.0 affects manufacturers in the apparel industry. We are going to illustrate this through a case study in a garment factory. There are several ways of advanced digital technologies that can assure high efficiency in the production. The actual production process is batch flow and the company is implementing a new tool which is RFId (Radio-frequency identification or radiofrequency identification) technology. Connected an RFId Tag to a part of the product to be tracked, each piece can be monitored in real time, having all the location and traceability information and machine data in real time piece by piece. Items and products can be monitored as they move through the factory allowing for quick and automatic identification without errors. This allow to maximize the use of production resources and correctly optimize stocks of raw materials.
Journal section: TECHNOLOGICAL BASIS OF “INDUSTRY 4.0”
Additive Manufacturing in the Scope of Industry 4.0: A Review on Energy Consumption and Building Time Estimation for Laser Powder Bed-Fusion Processespg(s) 118-122
The paradigm of Industry 4.0 pushes additive manufacturing (AM) from rapid prototyping towards the position of series production. Especially in metal 3D printing, increased attention is being paid to the topics of sustainability and resource efficiency. Energy demand during production and the calculation of building times play a decisive role here. Science has developed models for calculating energy consumption based on analytical and empirical approaches. Building time calculators have been introduced using a wide variety of analytical, analogical and parametric approaches. The present review summarizes the results and the state of the art, illustrates the results graphically and thus paves the way for further research approaches. The specific energy consumption per kilogram of processed material has risen over the last decades, which can be explained by higher technical requirements for production machines. Building time calculations continue to be subject to errors, depending on the type of calculation. The introduction of machine learning approaches has the potential to reduce this discrepancy.
Rapid progress in the field of industrialization and informatization methods has led to huge progress in the development of nextgeneration production technologies. The Internet of Things (IoT) is a pervasive technology, and now it is used in all areas of everyday life, from healthcare to technological production. The new industrial revolution began with connected technologies supported by the Internet of Things. However, the security of the Internet of Things is still an open question since in case of unauthorized access, data from sensors can be changed, for example, by a user with authorized access rights, which can lead to unforeseen consequences.
Big Data is becoming one of the most important technology trends. It presents a potential that is radically changing the way organizations use their information to be closer to customers by organizing in a way that benefits from the customer experience and transforms their business models.
Although Big Data is an ever-climbing trend in terms of industry, its meaning is still hidden by many conceptual ambiguities. The term is used to describe a wide range of concepts: from technological ability to storage, aggregation, data processing and finally their generation. In this paper the focus is at Big Data, because they are the technology of the future and in one way or another, they are affecting every field of industry. Furthermore, companies are increasingly trusting the possibility of using data as a valuable business asset to benefit and bring a competitive advantage compared to other companies. In the paper is presented also a SWOT Analysis that is conducted about Big Data information showing the strengths, weaknesses, opportunities, and risks that they carry. Also are presented the challenges of Big Data Technologies for the future. At the end of the paper, there are conclusions and recommendations about the topic.
The idea of creating and using digital twins has been strongly influenced by the process of integrating artificial intelligence methods with big data analytics of data from Internet of Things (IoT) devices. The concept of “Digital Twin” has become increasingly influential and culminating in the field of CPS. The main objective of the study is to define the basic requirements to the digital twins for cyber-physical system and based on the different definitions and components of digital twins, to summarize and analyze approaches, methods and tools used for their development. This analysis should serve as a basis for the development of a methodology for creating digital twins for cyber-physical manufacturing systems in the process industry.
The digital twin (DT) based on CMM as support Industry 4.0, are based on integration of digital product metrology information through metrological identification, application artificial intelligence techniques and generation of global/local inspection plan for coordinate measuring machine (CMM). DT based on CMM has an extremely expressed requirement for digitalization, control, and monitoring of the measurement processes inside Industry 4.0 concept. This paper presents an approach of development DT as one direction information flow based on four levels: (i) mathematical model of the measuring sensor path; (ii) tolerances and geometry of the parts by applying an ontological knowledge base; (iii) the application of AI techniques such as Ants Colony Optimization (ACO) and Genetic lgorithm (GA) to optimize the measurement path, part number of part setup and configuration of the measuring probes; (iv) simulation of measurement path. After simulation of the measurement path and visual checks of collisions, the path sequences are generated in the control data list for appropriate CMM. The experiment was successfully carried out on the example of prismatic part.
A system for classification of human facial and body emotions based on deep learning neural networkspg(s) 46-49
Current paper presents development of system intended to classify human facial and body emotions. It is based on two deep learning neural networks (DNN): – first one used for facial emotion recognition (FER) and second one for body gesture emotion recognition (BER). Combination of the results obtained by the two modalities (facial expression data and body gestures language data) provides more accurate results instead of these obtained using only one modality. After brief analysis of the available pre-trained DNN and datasets for facial and body emotions recognition, based on previous authors’ developments, the selection of two DNN models has been done. They are used in the development and verification of present system.
This article describes the actual trends and applications in industry where artificial intelligence models are deployed. This paper provides a more detailed description of the principles and methods of deploying models in the field of quality evaluation in industry and also in the areas of predictive maintenance and data analytics in the manufacturing process. Computer vision is increasingly coming to the fore due to its wide range of applications – object detection, categorisation of objects, reading QR codes and others. The area of predictive maintenance is important in terms of reducing downtime and saving costs for machine components. Models designed for data analytics, in turn, help to optimize the parameters of the production process so that the desired parameter is maximized or its optimal value is achieved.
Ultra-short laser patterning of silk fibroin thin films – a potential scaffold platform in tissue engineering applicationspg(s) 14-17
Silk-based scaffolds are specifically investigated in various tissue engineering applications, including for cartilage, bone, nerve, muscle, skin, or corneal regeneration. Guiding muscle cell growth is a challenging task in muscle tissue engineering. In this work, a selfassembled silk fibroin thin films were processed by ultra-short laser radiation to investigate its potential for guiding muscle cell proliferation. The ultra-short laser processing of silk fibroin (SF) have produced micro channels which are suitable for self-assembling and orientation of muscle cells and provides a niche for its attachment. Silk fibroin is an excellent candidate as a biomaterial for tissue engineering applications. Moreover, bacterial biofilm formation on surfaces are associated with persistent microbial contamination. Thus, recently new approaches are needed to impede bacterial surface colonization. Using femtosecond laser irradiation (wavelength 800 nm), laser-induced surface microstucturing is applied to achieve non-thermal, precise, and crack free surface processing with different topographical designs on silk fibroin thin films in order to enhance repelling of bacteria attachment.
Continuous development of technology brings daily improvements implemented in various processes, systems, machines, tools, or equipment. The development of these technologies is currently most often in the synergy of the Industry 4.0 strategy, which forms a solid foundation for modern industrial practice. In this continuously evolving environment of industrial practice, digital concepts for every manufacturing sector come to the fore. Part of every production sphere is the worker, the person forming part of the production process, who undoubtedly requires the same attention as the production system itself. The ergonomics industry deals with the issue of the humanization of technology in the workplace, where it is necessary to ensure the adaptation of the machine to humans and not by suitable working conditions. The presented article is focused on highlighting and describing the basic connections between the general principles of ergonomics, the principles of modern understanding of ergonomics in digital form, which is rapidly developing in the engineering industry in conjunction with Industry 4.0 strategy for practice. The conclusion of the article provides a general summary of the issue with the ideas of developing the concept of ergonomics software solutions in mechanical engineering. This article was supported by research grants VEGA 1/0431/21 and KEGA 004TUKE-4/2020.
One of the most important tasks on the edge between natural language processing (NLP) and computer vision (CV) is image captioning. There are many papers dedicated to researches in a field of improving image captioning models quality. However, compression of such models in order to be used on mobile devices is quite underexplored. More than that, such an important technique as knowledge distillation which is widely used for model compression isn’t mentioned in almost any of them. To fill this gap we applied the most efficient knowledge distillation approaches to several state-of-the-art image captioning architectures.
In the last ten years, the development and implementation of robotics, sensor and digital technology in the world from introduced us the third industrial revolution to the fourth industrial revolution. In its development strategy, Germany introduces digital technologies in production processes called “Industry 4.0” in 2011. The German example is followed by the following countries: USA, Great Britain, Sweden, Japan and other. Almost all technologically developed countries strive to introduce advanced technologies into production processes in order to maintain their competitive positions in the market. The implementation of the fourth technological revolution depends on a number of new and innovative technological achievements, i.e., the implementation of patents for the basic technologies of Industry 4.0. It is necessary to integrate production processes in all phases of product development, as well as monitoring during its working life through the use of advanced technologies. When automating production processes, we must include intelligent sensors, intelligent robots and connect everything to the Internet using digital technologies that closely monitor the product development process. It is also required to collect large amounts of data through network communication used during the production process. The paper presents a structural network with all levels for the implementation of Industry 4.0 in the production process of the metal industry.