In this paper, we present and discuss an innovative approach to solve Job Shop scheduling problems based on machine learning techniques. Traditionally, when choosing how to solve Job Shop scheduling problems, there are two main options: either use an efficient heuristic that provides a solution quickly, or use classic optimization approaches (e.g., metaheuristics) that take more time but will output better solutions, closer to their optimal value. In this work, we aim to create a novel architecture that incorporates reinforcement learning into scheduling systems in order to improve their overall performance and overcome the limitations that current approaches present. It is also intended to investigate the development of a learning environment for reinforcement learning agents to be able to solve the Job Shop scheduling problem. The reported experimental results and the conducted statistical analysis conclude about the benefits of using an intelligent agent created with reinforcement learning techniques. The main contribution of this work is proving that reinforcement learning has the potential to become the standard method whenever a solution is necessary quickly, since it solves any problem in very few seconds with high quality, approximate to the optimal methods.

Fiber reinforced composites are widely used in the production of parts for load bearing structures. It is generally recognized that composites can be affected both by monotonic and cyclic loading. For assembly purposes, drilling is needed, but holes can act as stress concentration notches, leading to damage propagation and failure. In this work, a batch of carbon/epoxy plates is drilled by different drill geometries, while thrust force is monitored and the hole’s surrounding region is inspected. Based on radiographic images, the area and other features of the damaged region are computed for damage assessment. Finally, the specimens are subjected to Bearing Fatigue tests. Cyclic loading causes ovality of the holes and the loss of nearly 10% of the bearing net strength. These results can help to establish an association between the damaged region and the material’s fatigue resistance, as larger damage extension and deformation by cyclic stress contribute to the loss of load carrying capacity of parts.

Composite materials are used in a substantial number of products. Environmental concerns highlight the need for the inclusion of recovered waste in their formulation, thus reducing their carbon footprint. These solutions raise the need to confirm the mechanical characteristics of these materials, avoiding unwanted failures. In this work, the authors present an experimental study on the drilling effects on fibrous–particulate hybrid composites made of glass/carbon fabrics and three different micro-inclusions: silica particles, recycled carbon fibre powder and cement. The mechanical features of the plates are confirmed by thrust force monitoring during drilling and by flexural testing. The range of results confirm the mechanical outcomes due to machining. The plates with monolithic carbon fabric or with carbon fabric plies in the outer plies returned higher mechanical characteristics. The plates with micro-inclusions had enhanced the flexural strength by 23% and 10%, in 40% and 60% fabric plates, respectively. The results demonstrate that the use of alternative formulations with micro-inclusions from recovered waste can contribute both to the reduction of the mechanical degradation of drilled hybrid composites and to environmental purposes by avoiding the increase in landfill waste.

Composite materials are increasingly being implemented in various solutions, ranging from conventional applications, like furniture, to more advanced ones, such as aerospace, based on their excellent properties, such as high mechanical strength and low weight. There are applications in which these materials are coupled to other parts. To achieve this connection, drilling processes are commonly used. Drilling causes irreversible damage to the material, which influences the mechanical strength of the plates. This study was conducted on 48 carbon/epoxy plates, each with two drilled holes, based on DOE (design of experiments) and the Taguchi method to design the experimental plan and to validate the results. Three control factors were considered for drilling: drill bit type, cutting speed, and feed rate, as it is expected that a low feed rate and a high cutting speed is the drilling configuration that inflicts the least damage. Subsequently, these specimens were subjected to enhanced radiography and an image analysis processing tool based on MatLab^® to assess the data collected and compute damage results. At the end, in analyzing the results of the Taguchi method, it is possible to validate the assumptions on the influence of the drilling process in delamination extension.