This study aims to systematically experimental investigate the influence of infill-patterns (IPs) on specific mechanical responses of parts fabricated by fused deposition modeling (FDM). A poly-lactic-acid (PLA) feedstock filament is utilized in the manufacturing process. Furthermore, six types of infill-patterns (deposition angle), namely full honeycomb, rectilinear, triangular, fast honeycomb, grid, and wiggle, are designed and printed. In order to determine the mechanical properties of manufactured parts, tensile tests are carried out. The mechanical properties such as extension, stress, elongation, energy, and Young’s modulus are considered as objective functions. As a result, there is a direct correlation between mechanical properties and infill patterns. Thus, it is essential to select the best infill-pattern in terms of their applications, giving sufficient strength without overdoing time and cost. Based on the results, a triangular infill-pattern has a maximum value of ultimate tensile strength and E-module (15.4 and 534 MPa, respectively). On the other hand, the wiggle pattern is more flexible.

Integrating machine learning algorithms leveraged by advanced data acquisition systems is emerging as a pivotal approach in predictive maintenance. This paper presents the deployment of such an integration on an industrial air compressor unit. This research combines updated concepts from the Internet of Things, machine learning, multi-sensor data collection, structured data mining, and cloud-based data analysis. To this end, temperature, pressure, and flow rate data were acquired from sensors in contact with the compressor. The observed data were sent to the Structured Query Language database. Then, a Linear Regression model was fitted to the training data, and the optimized model was stored for real-time inference. Afterward, structured data were passed through the model, and if the data exceeded the determined threshold, a warning email was sent to an operator. Adopting the Internet of Things enhances surveillance for specialists, decreasing the failure and damage probabilities. The model achieved 98% accuracy in the Mean Squared Error metric for our regression model. By analyzing the gathered data, the implemented system demonstrates the capabilities to predict potential equipment failures with promising accuracy, facilitating a shift from reactive to proactive maintenance strategies. The findings reveal substantial potential for improvements in maintenance efficiency, equipment uptime, and cost savings.

Wind turbines are known to be the most efficient method of green energy production, and wind turbine blades (WTBs) are known as a key component of the wind turbine system, with a major influence on the efficiency of the entire system. Wind turbine blades have a quite manual production process of composite materials, which induces various types of defects in the blade. Blades are susceptible to the damage developed by complex and irregular loading or even catastrophic collapse and are expensive to maintain. Failure or damage to wind turbine blades not only decreases the lifespan, efficiency, and fault diagnosis capability but also increases safety hazards and maintenance costs. Hence, non-destructive testing (NDT) methods providing surface and subsurface information for the blade are indispensable in the maintenance of wind turbines. Damage detection is a critical part of the inspection methods for failure prevention, maintenance planning, and the sustainability of wind turbine operation. Industry 4.0 technologies provide a framework for deploying smart inspection, one of the key requirements for sustainable wind energy production. The wind energy industry is about to undergo a significant revolution due to the integration of the physical and virtual worlds driven by Industry 4.0. This paper aims to highlight the potential of Industry 4.0 to help exploit smart inspections for sustainable wind energy production. This study is also elaborated by damage categorization and a thorough review of the state-of-the-art non-destructive techniques for surface and sub-surface inspection of wind turbine blades.

In an increasingly competitive industrial world, the need to adapt to any change at any time has become a major necessity for every industry to remain competitive and survive in their environments. Industries are undergoing rapid and perpetual changes on several levels. Indeed, the latter requires companies to be more reactive and involved in their policies of continuous improvement in order to satisfy their customers and maximize the quantity and quality of production, while keeping the cost of production as low as possible. Reducing downtime is one of the major objectives of these industries of the future. This paper aimed to apply machine learning algorithms on a TA-48 multistage centrifugal compressor for failure prediction and remaining useful life (RUL), i.e., to reduce system downtime using a predictive maintenance (PdM) approach through the adoption of Industry 4.0 approaches. To achieve our goal, we followed the methodology of the predictive maintenance workflow that allows us to explore and process the data for the model training. Thus, a comparative study of different prediction algorithms was carried out to arrive at the final choice, which is based on the implementation of LSTM neural networks. In addition, its performance was improved as the data sets were fed and incremented. Finally, the model was deployed to allow operators to know the failure times of compressors and subsequently ensure minimum downtime rates by making decisions before failures occur.

Inspection methods, also known as non-destructive evaluation (NDE), is a process for inspecting materials, products, and facilities to identify flaws, imperfections, and malfunctions without destruction or changing the integrity of materials, structures, and mechanisms. However, detecting those defects requires test conducting and results inferring, which is highly demanding in terms of analysis, performance, and time. New technologies are therefore needed to increase the efficiency, probability of detection, and interpretability of NDE methods to establish smart inspection. In this context, Artificial intelligence (AI), as a fundamental component of the Industry 4.0, is a well-suited tool to address downsides associated with the current NDE methods for analysis and interpretation of inspection results, where methods integrating AI into their inspection process become automated and are known as smart inspection methods. This article sheds a light on the conventional methods and the smart techniques used in defects detection. Subsequently, a comparison between the two notions is presented. Furthermore, it investigates opportunities for the integration of non-destructive evaluation (NDE) methods and Industry 4.0 technologies. In addition, the challenges hindering the progress of the domain are mentioned as the potential solutions. To this end, along with Industry 4.0 technologies, a virtual inspection system has been proposed to deploy smart inspection.

The benefits of laser welding include higher production values, deeper penetration, higher welding speeds, adaptability, and higher power density. These characteristics make laser welding a superior process. Many industries are aware of the benefits of switching to lasers. For example, metal-joining is migrating to modern industrial laser technology due to improved yields, design flexibility, and energy efficiency. However, for an industrial process to be optimized for intelligent manufacturing in the era of Industry 4.0, it must be captured online using high-quality data. Laser welding of aluminum alloys presents a daunting challenge, mainly because aluminum is a less reliable material for welding than other commercial metals such as steel, primarily because of its physical properties: high thermal conductivity, high reflectivity, and low viscosity. The welding plates were fixed by a special welding fixture, to validate alignments and improve measurement accuracy, and a Computer-Aided Inspection (CAI) using 3D scanning was adopted. Certain literature has suggested real-time monitoring of intelligent techniques as a solution to the critical problems associated with aluminum laser welding. Real-time monitoring technologies are essential to improving welding efficiency and guaranteeing product quality. This paper critically reviews the research findings and advances for real-time monitoring of laser welding during the last 10 years. In the present work, a specific methodology originating from process monitoring using Computer-Aided Inspection in laser-welded blanks is reviewed as a candidate technology for a digital twin. Moreover, a novel digital model based on CAI and cloud manufacturing is proposed.