Laser Powder Bed Fusion (LPBF) has emerged as a leading additive manufacturing (AM) process for producing complex metal components. Despite its advantages, the inherent LPBF process complexity leads to challenges in achieving consistent quality and repeatability. To address these concerns, recent research efforts have focused on sensor fusion techniques for process monitoring, and on developing more elaborate control strategies. Sensor fusion combines information from multiple in situ sensors to provide more comprehensive insights into process characteristics such as melt pool behavior, spatter formation, and layer integrity. By leveraging multimodal data sources, sensor fusion enhances the detection and diagnosis of process anomalies in real-time. Closed-loop control systems may utilize this fused information to adjust key process parameters–such as laser power, focal depth, and scanning speed–to mitigate defect formation during the build process. This review focuses on the current state-of-the-art in sensor fusion monitoring and control strategies for LPBF. In terms of sensor fusion, recent advances extend beyond CNN-based approaches to include graph-based, attention, and transformer architectures. Among these, feature-level integration has shown the best balance between accuracy and computational cost. However, the limited volume of available experimental data, class-imbalance issues and lack of standardization still hinder further progress. In terms of control, a trend away from purely physics-based towards Machine Learning (ML)-assisted and hybrid strategies can be observed. These strategies show promise for more adaptive and effective quality enhancement. The biggest challenge is the broader validation on more complex part geometries and under realistic conditions using commercial LPBF systems.

This study addresses the need for advanced machine learning-based process monitoring in smart manufacturing. A methodology is developed for near-real-time part quality prediction based on process-related data obtained from a CNC turning center. Instead of the manual feature extraction methods typically employed in signal processing, a novel one-dimensional convolutional architecture allows the trained model to autonomously extract pertinent features directly from the raw signals. Several signal channels are utilized, including vibrations, motor speeds, and motor torques. Three quality indicators—average roughness, peak-to-valley roughness, and diameter deviation—are monitored using a single model, resulting in a compact and efficient classifier. Training data are obtained via a small number of experiments designed to induce variability in the quality metrics by varying feed, cutting speed, and depth of cut. A sliding window technique augments the dataset and allows the model to seamlessly operate over the entire process. This is further facilitated by the model’s ability to distinguish between cutting and non-cutting phases. The base model is evaluated via k-fold cross validation and achieves average F1 scores above 0.97 for all outputs. Consistent performance is exhibited by additional instances trained under various combinations of design parameters, validating the robustness of the proposed methodology.

Selective laser melting (SLM) builds metal parts layer by layer by locally melting powder with a fine laser beam, generating complex, geometry-dependent temperature gradients that govern density, microstructure, defects, and residual stresses. Resolving these gradients with high-fidelity finite-element (FE) models is prohibitively slow because the temperature field must be evaluated at dense points along every scan track across multiple layers, while the laser spot is orders of magnitude smaller than typical layer dimensions. This study replaces FE analysis with a deep neural network that predicts the end-of-build temperature field orders of magnitude faster. A benchmark part containing characteristic shape features is introduced to supply diverse training cases, and a novel control-volume-based geometry-abstraction scheme encodes arbitrary workpiece shapes into compact, learnable descriptors. Thermal simulation data from the benchmark train the network, which then predicts the residual temperature field of an unseen, geometrically dissimilar part with a mean absolute error of ~10 K and a mean relative error of ~1% across 500–1300 K. The approach thus offers a rapid, accurate surrogate for FE simulations, enabling efficient temperature-driven optimization of SLM process parameters and part designs.

A crank press is converted into a smart fatigue testing machine for 3-point bending of polymer matrix composite specimens. The press is retrofitted with a load cell base for work holding, which monitors the bending force applied by the ram, a cycle counter recording the number of loading cycles, and a camera recording snapshots of the specimen area where failure is expected. A convolutional and Resnet neural networks are trained to recognize failure as an area of color change in camera images. Signal drop on the load cell signals failure onset, thus triggering monitoring by the camera and execution of the neural network. Acceptable proof-of-concept results encourage further automation of the setup.

Dedicated simulation software is used to create a dataset which for a particular sand-cast part and various casting parameter values provide casting quality metrics based on temperature and solidification evolution. Based on simulation data, ANNs are trained to predict the successful or failed filling of the mold (a classification problem), as well as the quality of the part through solidification time, maximum microporosity, maximum von Mises residual stress, maximum displacement of any point in the casting and total volumetric shrinkage (a regression problem). Such ANNs can provide augmented information much faster than the simulation model to the process planner. A third category of ANNs (of the regression type, too) determine the temperature evolution with time at an inaccessible point, where no thermocouple can be placed, from the measurement history at two other thermocouples close to it. This data comes from real-time monitoring during casting. Such ANNs can aid the process supervisor in a ‘digital shadow’ context. The issues associated with generalizing these predictors to become independent of specific part geometry are also discussed.