Vision technologies are used in both industrial and smart city applications in order to provide advanced value products due to embedded self-monitoring and assessment services. In addition, for the full utilization of the obtained data, deep learning is now suggested for use. To this end, the current work presents the implementation of image recognition techniques alongside the original the quality assessment of a Parabolic Trough Collector (PTC) reflector surface to locate and identify surface irregularities by classifying images as either acceptable or non-acceptable. The method consists of a three-step solution that promotes an affordable implementation in a relatively small time period. More specifically, a 3D Computer Aided Design (CAD) of the PTC was used for the pre-training of neural networks, while an aluminum reflector surface was used to verify algorithm performance. The results are promising, as this method proved applicable in cases where the actual part was manufactured in small batches or under the concept of customized manufacturing. Consequently, the algorithm is capable of being trained with a limited number of data.

The first and most important target of the industrial world is to offer products that appeal to customers’ demands (affordable prices), while at the same time, respect the global effort of CO₂ emissions reductions, which is required under strict emissions rules. There is, however, an apparent contradiction between the two concepts; productivity and sustainability, leading to two strategies—innovation economy and circular economy, respectively. To this end, this work aims, through modeling the long-term environmental impact of producing new goods in short terms (innovation economy) and impact of rebuying, repairing and reusing products for extended use (circular economy), to study the relationship between the two economies. For this purpose, the terms of innovation and circular economy are introduced and described, in order to define the environmental impact during the lifecycle of a product. Two products are assessed for this study—a well-known, medium price vehicle, as well as an expensive mobile phone with several generations. The cost of purchase and the recurring costs are used as indicators of environmental impact, instead of calculating the impact directly for the production phase, due to the enormous size of the production data that are desired. The results, despite being indicative of the modelling complexity, can still be used to pave the way towards a modelling framework, proving, at the same time, that innovation and circular economy are not contradictive concepts.

Laser-Based Powder Bed Fusion is one of the most widely used additive manufacturing processes, mainly due to its high-quality output. End users would greatly benefit from a virtual simulation of the process; however, the modelling of the process is very complicated and slow and therefore restricted mainly to academic users. In this work, a computationally efficient approach to the thermal modelling of PBF-LB/M is presented. This approach is based on the enthalpy method and the division of the simulation into three characteristic scales of the process. Despite the small runtime of the simulations, the model captures the critical phenomena of the process achieving sufficient accuracy.

Industries are leveraging the wire laser-beam-directed energy deposition (DED-LB) additive manufacturing (AM) process to manufacture and repair high-quality, defect-free, and cost-effective parts. However, expensive, non-easily accessible, and complex metrology equipment is needed to quantify part-related performance metrics such as cross-sectional dimensional accuracy and intrinsic defects. This information is necessary for establishing the operating process window and for the quality characterization of the part. Therefore, this work presents a methodology that combines information captured from a vision-based monitoring system with the output of Computed Tomography (CT) towards the knowledge generation and process optimization of wire DED-LB. The design of experiments as well as the interpretation of the results are achieved by employing Nested ANOVA where the dependency of cross-sectional stability on the laser power parameter is demonstrated, enabling, at the same time, the understanding of unstructured datasets where multiple parameters vary at different levels. Finally, this work can be the pillar for adopting new production and part requirements while also giving directions about the effect of control strategies on the part quality.