Automating assembly processes in High-Mix, Low Volume (HMLV) manufacturing remains challenging, especially for Small and Medium-sized Enterprises (SMEs). Consequently, many companies still rely on a significant amount of manual operations with an overall low degree of automation. The emergence of artificial intelligence-based algorithms offers potential solutions, enabling assembly automation compatible with multiple products and maintaining overall production flexibility. This paper investigates the application of the YOLO (You Only Look Once) object detection algorithm in an HMLV production line within an SME. The performance of the algorithm was tested for different cases, namely, (a) on different products having similar product features, (b) on completely new products, and (c) under different lighting conditions. The algorithm achieved precision and recall greater than 98 % and mAP50:95 greater than 97 % .

Laser wire-feed metal additive manufacturing (LWAM) is an innovative technology that shows many advantages compared with traditional manufacturing approaches. Despite these advantages, its industrial adoption is limited by complex parameter management and inconsistent process quality. To address these issues and improve geometric accuracy, this study explores how process parameters influence bead geometry. We conducted a parameter study varying laser power, wire feed rate, traverse speed, and welding angle. Using a full factorial design with a central composite design methodology, we assessed bead height and width. This allowed us to develop a model to estimate ideal process parameters. The findings offer a detailed analysis of parameter interactions and their effects on bead geometry, aiming to enhance geometric accuracy and process stability in LWAM. Moreover, we have evaluated the proposed process parameters from our developed model, which showed a significant enhancement to the overall quality. This was validated via printing a single layer and multi-layer structures. The quality of the final predicted sample using the proposed method was improved by 40% compared to the best sample produced for the Design of Experiment trials.

Polymer/metal assemblies are widely used in industry, especially the automotive industry, to get more cost efficient and light weight structures. Although they present many advantages, their assembly remains challenging. Laser welding is an effective solution. Indeed, it is fast, presents high design freedom, and does not require any interstitial material. Furthermore, surface pretreatment can tune mechanical resistance. However, the root causes of adhesion remain partly unknown. The existence of chemical bonding at the interface has already been established, but other adhesion phenomena, such as diffusion, remain to be investigated. The aim of this study is to investigate the existence of diffusion at the interface between the polymer and the metal after laser welding. Therefore, a common material combination was used: polyamide-6.6 and aluminum. A thin film of polyamide-6.6 was deposited on mirror-polished aluminum, and two depth profiles out and in the weld were acquired by ToF-SIMS and compared. The results show that the diffusion of aluminum occurs at the interface of polyamide-6.6, with a diffusion length of approximately 22 nm.

Laser joining of polymers to metals is a rising research subject due to the potential of considerably reducing the weight of structures. This article deals with the laser joining process between polypropylene and aluminum. Without pre-treatment, laser joining of these materials is not feasible, and the method applied in this study to circumvent this issue is a surface modification of aluminum with a pulsed laser to create mechanical interlocking for the heat conduction laser joining technique. Different patterns and various laser parameters are analyzed with the design of experiments to best understand the effects of each parameter along with microscopic observations. It is found that engraving weakens the mechanical properties of the aluminum samples. The compromise between the engraving depth and the mechanical properties of the samples is optimized, and the engraving process with a 0.28 mm line width, 27.3% density and 150 mm/s speed provides the highest mechanical performance of the assembly with minimum degradation of aluminum samples. Moreover, by adjusting the laser power and using power modulation below 300 W, the decomposition of polypropylene occurring at high temperatures is reduced to a minimum. After the final optimization, the joined samples reliably withstand a maximum force of 1500 N, which is, approximately, a shear strength of 20 MPa.

Collaborative robots or cobots are one of the core technologies of Industry 4.0 as they can collaborate with the workers to perform tasks. This feature of cobots makes them an alternative to conventional industrial robots as they are more flexible, lightweight, and more intuitive. Several industries have started using them in their production line due to the increasing need to move toward incorporating Industry 4.0 technologies. However, its implementation in small and medium-sized enterprises (SMEs) is still at an early stage. This chapter focuses on the challenges for SMEs when introducing cobots in their manufacturing line. Understanding these challenges will help the reader in identifying the right applications and approaches for implementing cobots for their manufacturing line.

A revolutionary computer-generated environment called mixed reality (MR) combines the real and virtual worlds. The MR environment can be created using two rapidly developing technologies: augmented reality (AR) and virtual reality (VR), with varying degrees of awareness of reality. With the introduction of Industry 4.0 (I4.0) in the manufacturing systems, AR and VR technologies have seen adoption in various stages of the product life cycle. AR can improve the manufacturing tasks such as quality inspection, assembly instructions, maintenance, and safety by enhancing reality with virtual aides. On the other hand, VR can be a beneficial technology for training activities. This chapter mainly focuses on different AR systems and their interaction modalities. Moreover, the chapter also covers system architectures for two different AR systems (handheld devices and head-mounted devices) and validates the architectures with relevant case studies. Finally, a brief description of the VR technology is presented with a relevant case study.

Laser beam welding of miscellaneous material combinations is an effective joining technology useful for diverse industrial applications because it can provide high speed, flexibility, and precision. However, welding defects like solidification cracking are some of the challenges in the joining process. The past decade has seen an extended effort to deal with this issue in many studies. However, there remains to be more comprehensive research regarding preventive procedures for solidification cracking by changing the grain structure. Following a thorough understanding of the solidification crack mechanism theories, we reviewed recent research on the critical role of metallurgical factors in the solidification cracks during laser welding. It considers the influence of the grain structure, intermetallic compounds, and laser welding parameters to propose preventive procedures to suppress the solidification cracks. Recent achievements show grain refiners, laser beam oscillation, ultrasonic vibration, and implementation of double laser sources are the main strategies that suppress or minimize solidification cracks. Furthermore, in laser beam welding of dissimilar materials, like steel-hard metal and copper-aluminum, brittle intermetallic compounds are recognized as one of the main reasons for the solidification crack susceptible increment. Recent approaches to overcome the formation or reduce the number of intermetallic compounds through various laser parameters and setups are discussed.

Robotic drilling has advantages over traditional computer numerical control machines due to its flexibility and dexterity and the potential for rapid production and process automation. The dexterity and reach of the robotic drill end-effector enable the efficient drilling of large composite components, such as aircraft wing structures. Due to the anisotropy and inhomogeneity of fibre-reinforced polymer composite materials, drilling remains a challenging task. Inspection of the drilled hole is required at the end of the process to ensure that the final product is free from defects. Typically, such inspections require the parts to be transferred to a dedicated inspection station, which is a time-consuming non-value-added task and impractical for large components. In the interest of an efficient and sustainable manufacturing process, this work proposes a hybrid classification model implemented with a robotic drilling system to investigate the quality of drilled holes in situ. The classifier is trained and tested with a random selection of drilled holes, and the most accurate classifier is implemented. The selected classifier returns 90

Increasing product customization and shortening product life cycles in an ever-changing world is challenging for automation. This is especially true for assembly tasks, requiring a high level of perception, skill, and adaptability. With the rise of smart manufacturing, intelligent manufacturing, and other aspects related to Industry 4.0, the hurdles for automation of the aforementioned tasks are getting reduced. Especially Artificial Intelligence (AI) is expected to enable smart and flexible automation since it is possible to deduct decisions from unknown multidimensional correlations in sensor data, which is critical for the assembly of highly customized products. In this research paper, three different conventional and AI-based glue detection models are proposed with the target to automate a gluing process in a manual assembly of highly customized products in a batch size one production scenario. A conventional, one-dimensional rule-based model, and two hybrid models using a support vector machine image classifier (SVM) and either Tamura features or convolutional neural network (CNN) feature extraction are presented and compared. The obtained results demonstrate the efficiency and robustness of AI-based algorithms, as the CNN and SVM hybrid model outperforms the other two approaches achieving a prediction accuracy of >99% at the fastest classification speed.

Laser Wire-Feed Metal Additive Manufacturing (LWAM) is a process that utilizes a laser to heat and melt a metallic alloy wire, which is then precisely positioned on a substrate, or previous layer, to build a three-dimensional metal part. LWAM technology offers several advantages, such as high speed, cost effectiveness, precision control, and the ability to create complex geometries with near-net shape features and improved metallurgical properties. However, the technology is still in its early stages of development, and its integration into the industry is ongoing. To provide a comprehensive understanding of the LWAM technology, this review article emphasizes the importance of key aspects of LWAM, including parametric modeling, monitoring systems, control algorithms, and path-planning approaches. The study aims to identify potential gaps in the existing literature and highlight future research opportunities in the field of LWAM, with the goal of advancing its industrial application.

Augmented Reality (AR) applications are beginning to see rapid adaptation in the manufacturing sector. AR systems in the manufacturing industry can assist operators in simple manufacturing tasks, such as virtual instructions, as well as complex remote assistance and maintenance tasks. There are many ways to interact with AR content, commonly known as interaction modalities. These modalities are classified into three categories: touch, touchless, and wearable, or sometimes a combination of more than one modality known as multimodal interfaces. However, in the manufacturing industry, there is no one-size-fits-all solution regarding the interaction with AR content. Current research explores various input interaction modalities in AR and assesses the advantages & disadvantages associated with them in the manufacturing context. We adopt both touch and touchless modalities in our case study of assembling a planetary gear and present the merits and demerits of each modality assessing the extent of natural user interaction with AR content. Interaction with a wearable AR system is not part of this investigation.

Predictive maintenance is a proactive maintenance process based on the permanent monitoring and evaluation of machine data, using techniques and models from the fields of data science, machine learning and mechanical engineering. The aim is to increase equipment reliability and availability, minimize maintenance costs, avoid unexpected downtime and costly repairs, resulting in higher operational efficiency and productivity. This study analyses a high-speed, high-throughput machine producing paper and board products under critical environmental conditions such as temperature and humidity. There, short machine stops have a enormous impact on overall equipment effectiveness (OEE). However, the reasons for the machine downtimes are unclear. Hence, the critical parameters of the process were investigated to determine the relationship between machine stops and sensor data.In addition, three machine learning models were trained and evaluated with the data collected from the sensors.Through data analysis, it was found that the vacuum signals and torque peaks were responsible for the short machine stops. These, in turn, were interfering with systems that apply fluids. These results are the beginning of a roadmap for predictive maintenance of high-speed manufacturing machines

The concept of Circular Economy (CE) is gaining increasing attention as an indispensable renewal of linear economy without neglecting sustainable development goals. Closing resource loops and keeping resources in the system at the highest level of use for as long as possible are cited as the main goals of CE. However, due to missing information exchange, the lack of consistency between the existing end-of-life (EOL) infrastructure and the respective product designs hinders a successful circularity of resources. This research presents a method to collect, process, and apply EOL process data to provide the beginning-of-life (BOL) with important EOL-knowledge through a CE-adapted product design assessment. EOL-data is collected using a Circular Value Stream Mapping (C-VSM), EOL-information is processed using a digital state flow representation, and EOL-knowledge is applied by providing a decision-support tool for product designers in the context of a PET bottle case study in Luxembourg. The goal is to anticipate a circular flow of resources by reflectively aligning product design with the relevant EOL infrastructure. In contrast to the linear economy, the developed method makes it possible to consider not only the requirements of users but also the actual end users, the EOL process chains, when designing products.

There has been a rapid increase in the use of collaborative robots in manufacturing industries within the context of Industry 4.0 and smart factories. The existing human–robot interactions, simulations, and robot programming methods do not fit into these fast-paced technological advances as they are time-consuming, require engineering expertise, waste a lot of time in programming and the interaction is not trivial for non-expert operators. To tackle these challenges, we propose a digital twin (DT) approach for human–robot interactions (HRIs) in hybrid teams in this paper. We achieved this using Industry 4.0 enabling technologies, such as mixed reality, the Internet of Things, collaborative robots, and artificial intelligence. We present a use case scenario of the proposed method using Microsoft Hololens 2 and KUKA IIWA collaborative robot. The obtained results indicated that it is possible to achieve efficient human–robot interactions using these advanced technologies, even with operators who have not been trained in programming. The proposed method has further benefits, such as real-time simulation in natural environments and flexible system integration to incorporate new devices (e.g., robots or software capabilities).

The advancement in robotics and automation in manufacturing has resulted in tremendous productivity improvements. However, several tasks still require human intervention due to their unmatched cognitive capabilities, dexterity, proficiency and adaptability. The use of collaborative robots to work in close proximity with humans is one of the steps adapted by the manufacturing sector to increase the flexibility of human-robot interaction. However, the current interfaces (teach pendants, computer consoles) for programming such robots are complicated, unintuitive and unsuitable for spontaneous interactions. To fully utilize the benefits of collaborative robots, a user-friendly interface allowing workers with non-robotics background to intuitively and safely collaborate with such systems is needed. More recently, augmented reality (AR) tools have shown great potential for creating intuitive robot interfaces. Such interfaces allow the users to command and interact with the robots intuitively using natural gestures and speech while maintaining their concentration on the actual task. In this work, we will investigate the application of AR using a head-mounted display (HMD), specifically the Microsoft HoloLens in helping the worker to intuitively perform tasks by interacting with the collaborative robot. We will present a simulation study using the KUKA LBR IIWA robot to perform different tasks. The teleoperation of the robot will be done with an intuitive interface designed uniquely for HoloLens using the Unity software. The user will be provided with manipulation gestures native to the HoloLens, voice commands and overlaid holographic controls to perform the action on the robot. Through this work, we aim to demonstrate the improvements in the collaboration between human workers and robots to perform tasks in shared workspaces. Such outcomes will help the worker to adapt themselves in working together with the robots to perform different industrial operations efficiently.

Laser welding of copper and aluminum is challenging due to the formation of complex intermetallic phases. Only a defined amount of Al and Cu can be melted because of the limited solubility of Al–Cu systems. Finding the optimum melting is critical for a strong joint. Optical emission during the welding process contains the metal vapor of Al metal that is being welded. This is a good indicator for monitoring the welding process. This research paper focuses on the optical emission of Al from the bottom sheet during welding of Cu (top) and Al (bottom) in overlapped configuration for a spiral trajectory. The emitted signal in the range of 395 nm (±3 nm) from the bottom sheet of aluminum is used to identify excessive Cu–Al welding. The tensile shear strength, microstructure, and welding signal in the time domain for optimum and excessive weld conditions are investigated. In this study, a technique using a photodiode is shown to identify the excessive melting of Al during the welding process in real time.

Laser Wire Additive Manufacturing (LWAM) is a flexible and fast manufacturing method used to produce variants of high metal geometric complexity. In this work, a physics-based model of the bead geometry including process parameters and material properties was developed for the LWAM process of large-scale products. The developed model aimed to include critical process parameters, material properties and thermal history to describe the relationship between the layer height with different process inputs (i.e., the power, the standoff distance, the temperature, the wire-feed rate, and the travel speed). Then, a Model Predictive Controller (MPC) was designed to keep the layer height trajectory constant taking into consideration the constraints faced in the LWAM technology. Experimental validation results were performed to check the accuracy of the proposed model and the results revealed that the developed model matches the experimental data. Finally, the designed MPC controller was able to track a predefined layer height reference signal by controlling the temperature input of the system.

The biomedical industry uses more and more polymer/metal hybrid assemblies because of the ability to combine the advantages and lower the inconveniences of both materials. The key is to assemble them. Among the high variety of existing assembling techniques, laser welding appears as an excellent option. It is a quick process allowing a great design flexibility, high reproducibility without intermediate material needed to create the adhesion, which is advantageous for biomedical applications. The laser welding process creates strong adhesion between dissimilar materials, but the root cause for adhesion is still unclear. The analytical challenge is to gain an information at the molecular level from an interface that is deeply buried between the two materials. Such a study requires extremely surface sensitive analytical methods, such as ToF-SIMS or XPS in order to detect chemical bonds, but also a method to expose the interface to the X-ray or ion beam. In order to investigate the chemical bonding at the interface between polyamide-6.6 and titanium, mirror polished titanium surfaces were prepared, on which a thin polyamide-6.6 film was spin-coated. The samples were laser welded, and after dissolving the polymer thin film, XPS and ToF-SIMS measurement were performed. The ToF-SIMS data interpretation was assisted by a principal component analysis. This multivariate analysis is rather common for ToF-SIMS data but is more rarely used to solve adhesion problems. This allowed to show the nature of the chemical bond at the interface and to propose a reaction mechanism.

Molecular communication (MC) is an emerging communication paradigm that allows bio-nanomachines (NMs) to communicate using biochemical molecules as information carriers. It can be used in many promising biomedical applications such as the Internet of Bio-Nano Things (IoBNT) for targeted drug delivery and healthcare applications. In particular, the blood-tissue barrier (BTB) inside the body forms the main communication pathway for molecular information exchange between the NMs as well as between the intrabody nanonetwork and the bio-cyber interface in the IoBNT network. However, overcoming this barrier by the molecules is one of the main challenges for MC in the body. Therefore, spatiotemporal modeling of MC across the BTB is of particular interest. In this article, we develop a mathematical model and stochastic particle-based simulator for MC over high spatiotemporal resolution between mobile NMs in the blood capillary and the surrounding tissue. The transmitting bio-NM is modeled as a moving sphere with a continuous emission pattern over a specific duration. In this work, the blood capillary characteristics, including the BTB and blood flow, are modeled and their effect is examined on the molecular received signal. In addition, we examined the impact of the emission duration, the elimination rate, and the separation distance on the molecular received signal. The numerical results are verified using the developed particle-based simulator. This work can help in the optimum design and development of the IoBNT systems based on MC for biomedical applications, such as smart drug delivery and health monitoring systems.

This paper presents a mathematical model and control of an air compressor used to inflate an air spring for a vehicle’s seat vibration isolation system. The novelty of this research is to find out an accurate model for the air compressor, which is carried out using ARX and ARMAX black-box models. Then, a PID controller is designed to regulate the rate pressure in the air spring using the MATLAB/Simulink toolbox. A comparison between the ARX and ARMAX models revealed that the results of the latter model are more accurate in describing the dynamics of the air spring based on the percentage of fitness, final prediction error, and the mean-square error.