Laser direct metal deposition is an advanced additive manufacturing technology suitably applicable in maintenance, repair, and overhaul of high-cost products, allowing for minimal distortion of the workpiece, reduced heat affected zones, and superior surface quality. Special interest is growing for the repair and coating of 2024 aluminum alloy parts, extensively utilized for a wide range of applications in the automotive, military, and aerospace sectors due to its excellent plasticity, corrosion resistance, electric conductivity, and strength-to-weight ratio. A critical issue in the laser direct metal deposition process is related to the geometrical parameters of the cross-section of the deposited metal trace that should be controlled to meet the part specifications. In this research, a machine learning approach based on artificial neural networks is developed to find the correlation between the laser metal deposition process parameters and the output geometrical parameters of the deposited metal trace produced by laser direct metal deposition on 5-mm-thick 2024 aluminum alloy plates. The results show that the neural network-based machine learning paradigm is able to accurately estimate the appropriate process parameters required to obtain a specified geometry for the deposited metal trace.

Fibre reinforced plastic composite materials are difficult to machine because of the anisotropy and inhomogeneity characterizing their microstructure and the abrasiveness of their reinforcement components. During machining, very rapid cutting tool wear development is experienced, and surface integrity damage is often produced in the machined parts. An accurate selection of the proper tool and machining conditions is therefore required, taking into account that the phenomena responsible for material removal in cutting of fibre reinforced plastic composite materials are fundamentally different from those of conventional metals and their alloys. To date, composite materials are increasingly used in several manufacturing sectors, such as the aerospace and automotive industry, and several research efforts have been spent to improve their machining processes. In the present review, the key issues that are concerning the machining of fibre reinforced plastic composite materials are discussed with reference to the main recent research works in the field, while considering both conventional and unconventional machining processes and reporting the more recent research achievements. For the different machining processes, the main results characterizing the recent research works and the trends for process developments are presented.

A cloud-based manufacturing process monitoring framework for online smart diagnosis services has been developed with the aim of performing tool condition monitoring during machining of difficult-to-machine materials. The proposed architecture allows to share process monitoring tasks between different resources, which can be geographically dislocated and managed by actors with different competences and functions. Distributed resources with enhanced computation and data storage capability allow to improve the efficiency of tool condition diagnosis and enable more robust decision-making, exploiting large information and knowledge sharing. Diagnosis on tool conditions is offered as a cloud service, using an architecture where the computing resources in the cloud are connected to the physical manufacturing system realising a complex cyber-physical system using sensor and network communication. Based on sensorial data acquired at the factory level, smart online diagnosis on consumed tool life and tool breakage occurrence is carried out through knowledge-based algorithms and cognitive pattern recognition paradigms. On the basis of the cloud diagnosis, the local server activates the proper corrective action to be taken, such as tool replacement, process halting or parameters change, sending the right command to the machine tool control.

Machining of titanium alloys is characterised by extremely rapid tool wear due to the high cutting temperature and the strong adhesion at the tool-chip and tool-workpiece interface, caused by the low thermal conductivity and high chemical reactivity of Ti alloys. With the aim to monitor the tool conditions during dry turning of Ti-6Al-4V alloy, a machine learning procedure based on the acquisition and processing of cutting force, acoustic emission and vibration sensor signals during turning is implemented. A number of sensorial features are extracted from the acquired sensor signals in order to feed machine learning paradigms based on artificial neural networks. To reduce the large dimensionality of the sensorial features, an advanced feature extraction methodology based on Principal Component Analysis (PCA) is proposed. PCA allowed to identify a smaller number of features (k = 2 features), the principal component scores, obtained through linear projection of the original d features into a new space with reduced dimensionality k = 2, sufficient to describe the variance of the data. By feeding artificial neural networks with the PCA features, an accurate diagnosis of tool flank wear (VB_max) was achieved, with predicted values very close to the measured tool wear values.