Figure 3 - uploaded by Muhammad Ali Kaleem
Content may be subject to copyright.
Similar publications
Introduction to the disruption of online music streaming to the music industry
Citations
... Thus, automated, or semi-automated optimisation based on artificial intelligence is often used to meet these requirements [20][21][22]. Despite recent developments in automated and semi-automated AI-based optimisation of 3D printing processes, especially for Industry 4.0 purposes, they are still at the beginning of their development [23,24]. The main applications were divided into parameter optimisation, and anomaly detection, and may be classified into different types of machine learning (ML) tasks, including regression, classification, and clustering [25]. ...
... The evaluation of the study results and their measurements showed that even a simple ANN can be effective in a really complicated task as presented in our case study. Compartmental studies showed that our results are similar to or better than the result of previous studies [19,[22][23][24][25][26][27][28][29]. We should be aware that the variability of 3D printing processes is so huge that each case may be hard to compare. ...
... Arc welding is an extremely important technology primarily embraced by the automobile manufacturing industry [1][2][3]. The adoption of arc-welding robots in the production process has yielded many benefits, including enhanced productivity, cost savings, and improved efficiency [4,5]. The arc-welding robot usually needs to be supplied with a stable voltage and current in the process of joining parts, but this is not easy to achieve in practice. ...
Arc-welding robots are widely used in the production of automotive bracket parts. The large amounts of fumes and toxic gases generated during arc welding can affect the inspection results, as well as causing health problems, and the product needs to be sent to an additional checkpoint for manual inspection. In this work, the framework of a robotic-vision-based defect inspection system was proposed and developed in a cloud–edge computing environment, which can drastically reduce the manual labor required for visual inspection, minimizing the risks associated with human error and accidents. Firstly, a passive vision sensor was installed on the end joint of the arc-welding robot, the imaging module was designed to capture bracket weldments images after the arc-welding process, and datasets with qualified images were created in the production line for deep-learning-based research on steel surface defects. To enhance the detection precision, a redesigned lightweight inspection network was then employed, while a fast computation speed was ensured through the utilization of a cloud–edge-computing computational framework. Finally, virtual simulation and Internet of Things technologies were adopted to develop the inspection and control software in order to monitor the whole process remotely. The experimental results demonstrate that the proposed approach can realize the faster identification of quality issues, achieving higher steel production efficiency and economic profits.
... Identifying anomalies enables the user to plan Aerospace -Fuel consumption prediction -A genetic algorithm-optimized neural network topology is designed to predict the fuel flow-rate of a transport aircraft -Feed-forward backpropagation, Levenberg-Marquardt algorithms, and genetic algorithms [25] -Aircraft failure times prediction -Predict when the failure will happen by aircraft type and age -Artificial neural networks and genetic algorithms [15] -Aircraft design cycle time reduction -AI is used to expedite the decision-making process in the early stages of the aircraft design process -fuzzy logic and neural network [14] Automotive -Driving Assistance and Autonomous Driving -State-of-the-art deep learning technologies used in autonomous driving -AI-based self-driving architectures, convolutional and recurrent neural networks, and reinforcement learning [17], [37] -Driver monitoring -Monitor drivers and identify driving tasks in vehicles -Kinect, Random Forest, and Feedforward Neural Network [13] -Vehicle manufacturing -Human-collaborative robot assembly in cyber-physical production. Manufacturing system produces products from scratch without any human intervention during the process -collaborative robots and additive manufacturing [12,53] Electronics -Diagnosis of electrical machines and drives ...
... Since material waste is the biggest concern in the present era of industry 4.0, additive manufacturing is an option to reduce such concern [12]. Here the process by which digital 3-D design data is used to build up components in layers by depositing materials [12]. ...
... Since material waste is the biggest concern in the present era of industry 4.0, additive manufacturing is an option to reduce such concern [12]. Here the process by which digital 3-D design data is used to build up components in layers by depositing materials [12]. The scanner module is 3D printed using an FDM 3D printer, as illustrated in Figure 17. ...
The main purpose of this work is to design and analyse an external pipeline inspection robot which can be adapted to pipelines of varying diameter using various design attachments. The designed and developed robot is a modular type, which contains three modules attached using a point-to-point surface clamping mechanism. The main advantage of the design is, it can be utilized in horizontal and inclined live pipelines for inspection. Since a new modular design of external pipeline inspection robot is designed and manufactured, it makes it more unique compared with other robots in the market and also makes it much easier for mounting the robot on to the pipeline, this robotic design has much high potential in the area of pipeline inspection industries, pipe manufacturing industry, and as well as in petroleum industry. Here the modules are manufactured using additive manufacturing.so overall module weight is made lighter and stronger even for this complex design. The mechanism involved for inspection is a circumferential scanning mechanism which contains scanner arc moving to and fro in 360 degrees, Along each step of the robot, the scanning occurs on the surface of the pipe with an array of sensors that are attached to a semi-circular arc which is designed and mounted to the center of the robot body since this arc is the main working mechanism, On FEA Analysis with ANSYS 19.2 software it is concluded that materials like PEEK, ASA, Pro PLA, etc. can be utilized for manufacturing. But Acrylonitrile styrene acrylate (ASA) material is most suitable for the robot to perform in an external environment.
... Furthermore, knowledge-based systems have also been used and applied for tender evaluation, conflict resolution, risk analysis, waste management, sustainability evaluations, etc [75; 76]. Despite recent and remarkable developments in automated and semi-automated AI-based optimisation of 3D printing operations, researchers have addressed many issues to solve [77]. The main applications focused on parameter optimisation, and anomaly detection, and may be classified into several kinds of machine learning techniques, including regression, classification, and clustering [78]. ...
Construction 3D printing is a form of additive manufacturing which represents a process of fabricating buildings or construction components from a digital file by depositing a building material layer by layer without any formwork support. In this research work, an application of the automated planning, which is an artificial intelligence (AI) technique, to construction 3D printers is presented. On this basis, AI planners, expressed in Planning Domain Definition Language (PDDL 2.1), are developed and employed to generate a sequence of operations comprehensible to the control system of a robotic manipulator system which is to perform specific concrete 3D printing tasks to produce two spatial objects with different geometry specifications. Accordingly, AI planners are executed based on requirements of printability checking and prefabrication in robotic construction 3D printers. The planned sequences will then be input to a robotic simulator framework that will allow the user to monitor the whole 3D printing process. Moreover, the performance of the approach has been examined and analyzed through scalability tests and the obtained results demonstrated that incrementing edges and layers of an object causes an increase in the planner runtime. The work described in this paper addresses a new application of AI concepts to the robotic additive manufacturing domain so far lacking in the scientific literature.
... Quality Inspection: We identified three review articles (Chouchene et al., 2020;Kaleem & Khan, 2020;Qi et al., 2020) that address industrial AI in the area of quality inspection. ...
... Three papers out of 25 deal with quality inspection by conducting reviews (Chouchene et al., 2020;Kaleem & Khan, 2020;Qi et al., 2020). These are briefly discussed below. ...
... In addition, a summary of scientific articles dealing with AI for quality control in smart industries highlights the challenges and benefits of using machine learning for visual inspection. Kaleem and Khan (2020) provide an overview of the use of additive manufacturing systems in Industry 4.0, particularly in the automotive and aerospace industries. It also presents an intelligent manufacturing model that integrates artificial intelligence into additive manufacturing systems to improve the overall efficiency of the manufacturing industry. ...
Remarkable advances in Deep Learning, a subfield of Artificial Intelligence (AI), have attracted considerable attention in recent years. One prominent example is DeepMind, a company working on the development of a general-purpose AI. After AI systems outperformed professional players in games such as Go and chess, DeepMind recently achieved another breakthrough in predicting protein folding. Using Deep Learning, protein structures can now be predicted with over 90 percent accuracy, replacing laboratory experiments for the first time in history. Becoming aware of the successful application of Deep Learning, numerous industrial companies started pilot projects to gain insights. Manufacturing companies, in particular, are faced with the question of how Deep Learning can be leveraged to realize a competitive advantage and what challenges need to be considered. In production environments, quality control is a core task often relying on visual techniques. One of the world's leading German multinational automotive suppliers has been using Automatic Optical Inspection (AOI) for quality assurance in electronics production for decades. Since Computer Vision with Deep Learning has the potential to improve visual quality inspection, the company intends to support its AOI systems with suitable Deep Learning approaches. In this context, the present dissertation aims to contribute to research and gather general knowledge about the application of Deep Learning in an AOI environment. To this end, several studies are conducted. Extensive structured literature reviews form the foundation for selected Deep Learning experiments, which represent the main focus of this thesis. The experiments are based on a dataset provided by the company, containing images of Printed Circuit Boards (PCBs) captured by an AOI camera. The characteristics of the real-world dataset affect both, the experimental design as well as the results. Contributing to debates on architecture selection and Transfer Learning for operational use, the experiments provide significant insights into factors influencing the performance of deep neural networks in machine vision tasks for defect detection on PCBs. Despite recent advances in Computer Vision through Vision Transformers, the results for the case at hand show that the inductive bias inherent in established Convolutional Neural Networks (CNNs) is better suited for inspection tasks on compartmentalized PCBs and that Transfer Learning can accelerate the training-to-production cycle. All studies reveal in different ways that Deep Learning can make a substantial contribution to the industry in the field of optical inspection.
... Therefore, it is necessary to seek out a new approach for enhancement of inclinometer performance. Today, the development of AI in the Industry 4.0 [16], [17] helps manufacturers to drive efficiency, improve quality and better manage supply chains with mimic "cognitive" functions of the machine that humans associate with the human mind for "learning" and "problem-solving". Machine and deep learning algorithms provide novel tools to cope with large datasets, learning intricate non-linear patterns from input information [18], [19] . ...
The paper presents a research of angular orientation based on a Microelectromechanical System (MEMS) accelerometer by using machine learning (ML) and deep learning (DL) model with architectures of deep neural networks (DNN). In the industrial environment, Artificial Intelligence (AI) plays a crucial role in automation which is a potential solution for better performance of inclinometer. This research was carried out to apply this intelligent model on the Inertial Measurement Unit (IMU) to accomplish the angular position. The experiment shows that the ML model correctly learns the relationship between acceleration and tracking angles via polynomial regression with an R-square of 0.99. The employed DL model with 4 hidden layers of 10 neurons achieves an accuracy of 99.99 \% and almost non-error performance. The acceleration acquisitions were obtained from MEMS accelerometer LSM9DS1 at a frequency of 50 Hz via microcontroller STM32F401RE. The ML and DNN model were designed based on platform Tensorflow with high processing accuracy. The Pan-Tilt Unit was used as the angle reference for static and dynamic tests. The traditional technique is used for comparison as well as verification of the proposed models. DL model has better precision over the ML model due to its high structure level with updating weight and error optimization from the neural network structure. Meanwhile, MC shows more stable results in dynamic circumstances.
... Adopted as part of the High-Tech Strategy 2020 Action Plan in 2011, Industry 4.0 is a strategic initiative of the German government developed to revolutionize the manufacturing process [36][37][38][39][40][41][42][43][44][45][46][47], by bringing together a set of pillars that enable the fusion of the physical, digital, human and biological worlds, fostering new technologies in the industrial environment, as illustrated in Fig. 1. Among these pillars, the introduction of the Internet of Things and Services in the factory environment [48] (also known as IIoT, Industrial Internet, Internet of Everything and Internet 4.0 [49]), can be highlighted for the emergence of the fourth industrial revolution. ...
The industrial scenario is undergoing exponential changes, mainly due to the different technologies that emerge quickly and the ever increasing demand. As a consequence, the number of processing devices and systems in the industries’ architectures is also increasing. Entities connectivity, physical/virtual joint functioning, interactivity, interoperability, self-organization, smart decision making, among other factors are fundamental to foster Industry 4.0 (I4.0) potential. We believe that Cyber Physical System (CPS) and Industrial Internet of Things (IIoT) will have a major role in the emerging I4.0. In this context, researchers and experts from major factories are exploring these technologies in order to keep up with this digital transformation, developing IIoT systems and CPS architectures capable of connecting network devices from different information and communications technologies (ICT) systems, virtualizing the companies’ assets and integrating them with other manufacturing sectors and companies. This article performs a survey covering the main CPS architecture models available in the industrial environment, emphasizing their key characteristics and technologies, as well as the correlations among them, pointing objectives, advantages and contribution for the IIoT introduction in I4.0. It also provides a literature review covering projects from CPSs and IIoT point-of-view, identifying main technologies employed in current state-of-the-art and how they can meet the I4.0 key features of vertical and horizontal industrial integration. Finally, the article points requirements for current and future challenges, limitations, gaps and necessary changes in the CPS architectures in order to improve and introduce them in the I4.0 scenario.
The advancement of Additive Manufacturing
(AM) technology has made it possible to build porous metal
scaffolds with high quality. Unlike traditional techniques,
the AM of porous scaffolds is distinguished by a precise and
controlled manufacturing process that allows regular pore
distribution at the micro-scale and the formation of predesigned
implants that are tailored for specific patients. Pores
serve as the microenvironment of ingrowing bone, and they
must have enough room for cells to adhere and proliferate.
The impact of AM porous metal scaffold on bone ingrowth
is influenced by the action of cells and bone ingrowth. In
the field of orthopaedics, AM uses have greatly expanded.
Anatomical models, surgical tools and tool design, splints,
implants, and prosthetics are among the applications for
additive manufacturing. A cursory examination of numerous
research articles reveals that patient-specific orthopaedic
procedures offer a variety of application areas as well as
potential development options. This paper focuses on AM
techniques, mechanical properties, porosity, pore structure,
surface modification, and other factors that may influence
bone ingrowth into AM porous metal scaffolds.
