Fig 1 - uploaded by Fotios K. Konstantinidis
Content may be subject to copyright.
The textile manufacturing factory is segmented in four production stages.
Source publication
As we move forward to the fourth industrial revolution, findings in the state-of-the-art enhance the technological advancements in the research community as well as the business one, in particular the textile manufacturing, being here reviewed.
In industry 4.0, the silos-free integrated systems sense the entire manufacturing environment by using se...
Citations
... For this reason, the funds invested in the automation of such processes are huge. According to the findings, the first priority in Industry 4.0 is the use of machine vision for quality control [37,75,94,98], with a percentage that even reaches 29%. This is followed by monitoring and detection of surface anomalies with a rate of 24% and 21%, respectively. ...
... Based on the findings of this research, quality control is the priority application, since, in the manufacturing sector, the quality of the products is decisive. Detection is also a fundamental task, such as detection, e.g., of surface irregularities [72], measurement, e.g., wear measurement [80], recognition, e.g., of materials [8], and monitoring [94]. ...
... More generally, in the automotive sector, machine vision is employed to observe human workers (body movements, Health and Safety (H&S) compliance) as well as guide vehicles with the aim of enhancing quality and correcting errors/defects in real-time. The dominant goal is to deliver constructions with zero defects at the human system level [94]. ...
The Fourth Industrial Revolution combined with the advent of artificial intelligence brought significant changes to humans’ daily lives. Extended research in the field has aided in both documenting and presenting these changes, giving a more general picture of this new era. This work reviews the application field of the scientific research literature on the presence of machine vision in the Fourth Industrial Revolution and the changes it brought to each sector to which it contributed, determining the exact extent of its influence. Accordingly, an attempt is made to present an overview of its use in the Fifth Industrial Revolution to identify and present the changes between the two consequent periods. This work uses the PRISMA methodology and follows the form of a Scoping Review using sources from Scopus and Google Scholar. Most publications reveal the emergence of machine vision in almost every field of human life with significant influence and performance results. Undoubtedly, this review highlights the great influence and offer of machine vision in many sectors, establishing its use and searching for more ways to use it. It is also proven that machine vision systems can help industries to gain competitive advantage in terms of better product quality, higher customer satisfaction, and improved productivity.
... Authors create a novel quantitative instrument for estimating the influence of the suggested solutions on the overall performance of the process chain [62]. As stated in an analysis of the applied machine vision systems in the automotive [63] and textile [64] industries, computer vision systems with self-adjustment capabilities should be integrated with existing execution systems to correct defects in real-time, thereby promoting the intelligent system design towards enabling ZDM [65,66]. In a recent study, insect-based retinal microscanning movements detect and locate contrasting objects, such as edges or bars, in a bioinspired active vision position sensing system [67]. ...
Quality constitutes the cutting-edge of contemporary industry, much more sharpened with the emergence of Industry 4.0. Yet, the assurance of delivering high-quality products remains a challenging problem that requires cautious controls and timely actions through the entire phases of the production cycle. To that end, zero-defect manufacturing (ZDM) has given prominence to a comprehensive methodology that ensures quality control and defects eradication at every phase of the procedure, prioritizing the continuous supervision of each distinctive component to satisfy the corresponding quality assurance standards. Continuous supervision and detection of possible flaws are subjective to exploiting high-tech sensors for high-precision monitoring and assessment. Considering the above, adopting active vision technology can further enhance the promising capabilities of ZDM. The paper highlights the active vision's benefits to the ZDM strategy and introduces a practical framework for applying such technology through the different stages. Innovations and challenges that have to be taken into consideration are also discussed.
... The mental burden received by the welding operator is that when welding small products, the operator must adjust the gas pressure, heat pressure, and others to match the desired product, if an error occurs during welding it can cause product defects such as bent, melted, charred, even can be perforated and unwanted things happen if the product that has been welded enters the finishing process, there are often parts of the product that have holes. Especially in the weld joint, which makes the finishing operator bring the product with visible holes and ask the welding operator for a patch [10]; [11]; [12], which can sometimes interfere with work because they have to adjust the level of gas pressure, heat, etc. In addition, another problem is that if the gas cylinder from the welding has run out, the operator must replace it by rotating a tube that is heavy and tall enough to be carried to the empty tube holder and bringing a new tube to be installed in the welding machine [13]; [14]; [15]. ...
This study aims to determine the mental workload of 15 respondents at PT. X in the morning shift and night shift, as measured by the Swedish Occupational Fatigue Index (SOFI) method. The highest value of the morning shift fatigue index dimension is found in the lack of energy factor with a value of 3.97, while in the night shift, the highest value is in the sleepiness factor with a value of 3.13. The fatigue index of workers is considered to be still high and work system improvements are needed.
... Due to the exponential advancements of Artificial Intelligence (AI) and Edge Computing (EC), Machine Vision (MV) technology stands as the eyes of the machines in the Smart Factory that capture the environment recognising events without human interaction [18]. Generally, the most common MV applications are object detection, parts counting, surface defect identification, paper reading and locating, quality measurement, and robotic guidance [19]. Nonetheless, the MV systems are not so popular in the occupational, H&S applications, despite the fact that there are some relevant applications, such as the autonomous AROWA (Autonomous RObot framework for Warehouse 4.0 health and safety inspection operations) platform that identifies H&S risks, informing the responsible systems [20]. ...
The Zero-Defect Manufacturing (ZDM) paradigm will drastically change the manufacturing system and its socio-technological interactions. Following the idea that 'quality is free', this is, the cost of appraisals is lower compared to defects, bigger effort will be placed in detect, predict, prevent, and repair. Such activities would require an adequate level of automation. Human operators are the ultimate flexible resource in the manufacturing system, thus should be appreciated and protected. Human Factors and Ergonomics (HF/E) have been studies for decades but not been part of Industry 4.0. To secure a true sustainable growth towards ZDM and Industry 5.0, humans should be the centre of such socio-technological revolution. Utilising state-of-the-art technologies, such as Machine Vision and Artificial Intelligence, and knowledge gained from the ergonomic science field, human-centred ZDM can be secured. In this paper, a RULA-based Machine Vision framework is proposed for the real-time assessment of human ergonomics in shop floor.
... Nowadays, such cameras are successfully utilized for mapping trajectories of up to 1000 km [40]. Beyond the sensor's low cost and its applicability to various mobile platforms, especially the ones with restricted computational abilities, e.g., unmanned aerial vehicles (UAVs) [61,100], the main reason for its utilization is related to the rich textural information presented in images [46,47], which provide a significant advantage over the other sensors permitting to capture the environment's appearance with high distinctiveness effectively [38]. Not surprisingly, modern robotic navigation systems are based on visual place recognition algorithms to detect loop closures [10,11,14,28,90,93,96] (see Figure 4.1). ...
As a mobile robot, e.g., an aerial, underwater, or ground‐moving vehicle, navigates through an unknown environment, it has to construct a map of its surroundings and simultaneously estimate its pose within this map. This technique is widely known in the robotics community as simultaneous localization and mapping (SLAM). During SLAM, a fundamental feature is loops’ detection, i.e., areas earlier visited by the robot, allowing consistent map generation. Due to this reason, a place recognizer is adopted, which aims to associate the current robot's environment observation with one belonging in the map. In SLAM, visual place recognition formulates a solution, permitting loops’ detection using only the scene's appearance. The main components of such a framework's structure are the image processing module, the map, and the belief generator. In this chapter, the reader is initially familiarized with each part while several visual place recognition frameworks paradigms follow. The evaluation steps for measuring the system's performance, including the most popular metrics and datasets, are also presented. Finally, their experimental results are discussed.
... On the contrary, technologies such as machine vision, digital twins, and additive manufacturing have not been analysed, in spite of their value. For example, machine vision is used not only to identify the quality of the products, but also to guide unmanned vehicles inside and outside the factory [89]. Additive manufacturing promotes sustainability by reducing the volume of raw materials, while digital twins predict upcoming production faults, allowing the machines to undergo self-configuration. ...
The rise of the fourth industrial revolution aspires to digitize any traditional manufacturing process, paving the way for new organisation schemes and management principles that affect business models, the environment, and services across the entire value chain. During the last two decades, the generated advancements have been analysed and discussed from a bunch of technological and business perspectives gleaned from a variety of academic journals. With the aim to identify the digital footprint of Industry 4.0 in the current manufacturing ecosystem, a systematic literature survey of surveys is conducted here, based on survey academic articles that cover the current state-of-the-art. The 59 selected high-impact survey manuscripts are analysed using PRISMA principles and categorized according to their technologies under analysis and impact, providing valuable insights for the research and business community. Specifically, the influence Industry 4.0 exerts on traditional business models, small and medium-sized enterprises, decision-making processes, human–machine interaction, and circularity affairs are investigated and brought out, while research gaps, business opportunities, and their relevance to Industry 5.0 principles are pointed out.
... The fourth industrial revolution is rapidly being occurred via the digitalisation of the manufacturing processes, the use of distributed processing, and the vertical/horizontal integration of the entire supply chain. Through this initiative, the interest of researchers turned to the industrial manufacturing field, yielding innovation and advancements, which can easily be applied in other industries or supportive stages such as storing and recycling [1]. In the warehouses, the digitalisation of the processes offers a fully automated ecosystem, where machines and humans harmonically coexist, improving the quality of services and the efficiency of production lines, while at the same time they keep the costs and the failures at low levels [2]. ...
Over the previous two decades, a tremendous impact has been created on each stage of the production value chain, through digitization of the traditional industrial processes and procedures. Since warehouses are at the heart of distributed supply chain networks, it is critical to leverage modern automation tools and through-engineering solutions to increase their efficiency and continuously meet the demanding standards. Towards this end, we describe the design of a health and safety (H&S) inspection robot capable of autonomously detecting hazard events without human intervention in warehouses. It makes use of computer vision (CV) techniques, edge computing (EC) and artificial intelligence (AI) to identify critical occurrences that have a detrimental impact on H&S. while counting available resources using inventory tracking methodologies. Furthermore, action-based modules are activated in response to the recognised event, informing warehouse workers about it and notifying other systems, operators and stakeholders, where appropriate, as foreseen by the protocol. Lastly, the conceptual architecture of the proposed autonomous robot is presented, which classifies the needed vision-based and action-based modules.
... At the same time, the authors in [11] proposed a way to produce a small, lightweight, and cheap platform on a single printed circuit board (PCB) aiming for robotic research [11]. Due to the wide use of quadrotors in applications [12], such as surveillance [13]- [15], search and rescue operations [16], [17], inspection [18], [19], mapping [20]- [23], and media production [24], flight safety is of the highest importance in autonomous navigation because of the possible hazards to people or disasters to their equipment in cases of malfunction [25]. A crowd detection method based on light and fast convolutional neural networks (CNNs) [26], [27] is demonstrated in [28]. ...
... The only machine vision system [20] capable to be part of a smart automotive factory comprises an open access architecture allowing it to be easily integrated with other systems. This trend also emerged in our analysis for textile manufacturing where the vast majority of vision-based textile application do not include integration capabilities with other key systems to enable the zero defect manufacturing [30]. ...
The challenging market of automotive industry urges the manufacturers worldwide to benefit from the incredible technological advancements of the fourth industrial revolution (Industry 4.0), which is in progress. This revolutionary era flourishes the sensing, processing and integration technologies across the systems, while the machine vision serves as the ``eyes" of the cyber-physical systems. This paper systematically provides a comprehensive analysis of the applied machine vision systems in the automotive industry over the last five years and anticipates the technology opportunities and future trends. The conducted analysis reveals that the machine vision technology is mainly employed for quality related purposes. Besides, fruitful advancements have occurred in the other automotive manufacturing domains, yet the horizontal and vertical integration is not a priority in their design. The authors conclude that computer vision systems empowered with self-adjustment capacities should be integrated with existing execution systems to rectify defects in real-time, thus promoting the intelligent system design towards enabling the zero defect manufacturing in human and system level.
