Masoud Deylami

Masoud Deylami, Negar Izadipour, Adel Alaeddini

Manufacturability assessment is a critical step in bridging the persistent gap between design and production. While artificial intelligence (AI) has been widely applied to this task, most existing frameworks rely on geometry-driven methods that require extensive preprocessing, suffer from information loss, and offer limited interpretability. This study proposes a methodology that evaluates manufacturability directly from parametric design features, enabling explicit incorporation of dimensional tolerances without requiring computer-aided design (CAD) processing. The approach employs Kolmogorov-Arnold Networks (KANs) to learn functional relationships between design parameters, tolerances, and manufacturability outcomes. A synthetic dataset of 300,000 labeled designs is generated to evaluate performance across three representative scenarios: hole drilling, pocket milling, and combined drilling-milling, while accounting for machining constraints and design-for-manufacturing (DFM) rules. Benchmarking against fourteen machine learning (ML) and deep learning (DL) models shows that KAN achieves the highest performance in all scenarios, with AUC values of 0.9919 for drilling, 0.9841 for milling, and 0.9406 for the combined case. The proposed framework provides high interpretability through spline-based functional visualizations and latent-space projections, enabling identification of the design and tolerance parameters that most strongly influence manufacturability. An industrial case study further demonstrates how the framework enables iterative, parameter-level design modifications that transform a non-manufacturable component into a manufacturable one.

Rahmat K. Adesunkanmi, Alexander W. Brandt, Masoud Deylami et al.

Accurately predicting the drift (displacement) of leeway objects in maritime environments remains a critical challenge, particularly in time-sensitive scenarios such as search and rescue operations. In this study, we propose a multi-modal machine learning framework that integrates Sentence Transformer embeddings with attention-based sequence-to-sequence architectures to predict the drift of leeway objects in water. We begin by experimentally collecting environmental and physical data, including water current and wind velocities, object mass, and surface area, for five distinct leeway objects. Using simulated data from a Navier-Stokes-based model to train a convolutional neural network on geometrical image representations, we estimate drag and lift coefficients of the leeway objects. These coefficients are then used to derive the net forces responsible for driving the objects' motion. The resulting time series, comprising physical forces, environmental velocities, and object-specific features, combined with textual descriptions encoded via a language model, are inputs to attention-based sequence-to-sequence long-short-term memory and Transformer models, to predict future drift trajectories. We evaluate the framework across multiple time horizons ($1$, $3$, $5$, and $10$ seconds) and assess its generalization across different objects. We compare our approach against a fitted physics-based model and traditional machine learning methods, including recurrent neural networks and temporal convolutional neural networks. Our results show that these multi-modal models perform comparably to traditional models while also enabling longer-term forecasting in place of single-step prediction. Overall, our findings demonstrate the ability of a multi-modal modeling strategy to provide accurate and adaptable predictions of leeway object drift in dynamic maritime conditions.