Yuecheng Cai

Yuecheng Cai, Jasmin Jelovica

Machine learning (ML) and deep learning (DL) techniques have gained significant attention as reduced order models (ROMs) to computationally expensive structural analysis methods, such as finite element analysis (FEA). Graph neural network (GNN) is a particular type of neural network which processes data that can be represented as graphs. This allows for efficient representation of complex geometries that can change during conceptual design of a structure or a product. In this study, we propose a novel graph embedding technique for efficient representation of 3D stiffened panels by considering separate plate domains as vertices. This approach is considered using Graph Sampling and Aggregation (GraphSAGE) to predict stress distributions in stiffened panels with varying geometries. A comparison between a finite-element-vertex graph representation is conducted to demonstrate the effectiveness of the proposed approach. A comprehensive parametric study is performed to examine the effect of structural geometry on the prediction performance. Our results demonstrate the immense potential of graph neural networks with the proposed graph embedding method as robust reduced-order models for 3D structures.

Runze Shi, Shengyu Yan, Yuecheng Cai et al.

Automated alpha discovery is difficult because the search space of formulaic factors is combinatorial, the signal-to-noise ratio in daily equity data is low, and unconstrained program generation is operationally unsafe. We present Hubble, an agentic factor mining framework that combines large language models (LLMs) with a domain-specific operator language, an abstract syntax tree (AST) execution sandbox, a dual-channel retrieval-augmented generation (RAG) module, and a family-aware selection mechanism. Instead of treating the LLM as an unconstrained code generator, Hubble restricts generation to interpretable operator trees, evaluates every candidate through a deterministic cross-sectional pipeline, and feeds back both top formulas and structured family-level diagnostics to subsequent rounds. The current system additionally introduces positive/negative RAG, formula-similarity penalties, standardized multi-metric scoring, dual reporting of RankIC and Pearson IC, and persistent diagnostics artifacts for post-hoc research analysis. On a U.S. equity universe of roughly 500 stocks, our main run evaluates 104 valid candidates across three rounds with zero runtime crashes and discovers a top set dominated by range, volatility, and trend families rather than crowded volume-only motifs. We then fix the resulting top-5 factors and validate them on a held-out period from 2025-06-01 to 2026-03-13. In this out-of-sample window, the two range factors and two volatility factors remain positive and several achieve HAC-significant Pearson IC and long-short evidence, whereas the weakest in-sample trend factor decays materially. These results suggest that safe LLM-guided search can be upgraded from a syntax-compliant generator into a reproducible alpha-research workflow that jointly optimizes validity, diversity, interpretability, and family-level generalization.

Siddharth Nand, Yuecheng Cai

Differential equations are used to model and predict the behaviour of complex systems in a wide range of fields, and the ability to solve them is an important asset for understanding and predicting the behaviour of these systems. Complicated physics mostly involves difficult differential equations, which are hard to solve analytically. In recent years, physics-informed neural networks have been shown to perform very well in solving systems with various differential equations. The main ways to approximate differential equations are through penalty function and reparameterization. Most researchers use penalty functions rather than reparameterization due to the complexity of implementing reparameterization. In this study, we quantitatively compare physics-informed neural network models with and without reparameterization using the approximation error. The performance of reparameterization is demonstrated based on two benchmark mechanical engineering problems, a one-dimensional bar problem and a two-dimensional bending beam problem. Our results show that when dealing with complex differential equations, applying reparameterization results in a lower approximation error.

Yuecheng Cai, Jasmin Jelovica

Surrogate models are essential in structural analysis and optimization. We propose a heterogeneous graph representation of stiffened panels that accounts for geometrical variability, non-uniform boundary conditions, and diverse loading scenarios, using heterogeneous graph neural networks (HGNNs). The structure is partitioned into multiple structural units, such as stiffeners and the plates between them, with each unit represented by three distinct node types: geometry, boundary, and loading nodes. Edge heterogeneity is introduced by incorporating local orientations and spatial relationships of the connecting nodes. Several heterogeneous graph representations, each with varying degrees of heterogeneity, are proposed and analyzed. These representations are implemented into a heterogeneous graph transformer (HGT) to predict von Mises stress and displacement fields across stiffened panels, based on loading and degrees of freedom at their boundaries. To assess the efficacy of our approach, we conducted numerical tests on panels subjected to patch loads and box beams composed of stiffened panels under various loading conditions. The heterogeneous graph representation was compared with a homogeneous counterpart, demonstrating superior performance. Additionally, an ablation analysis was performed to evaluate the impact of graph heterogeneity on HGT performance. The results show strong predictive accuracy for both displacement and von Mises stress, effectively capturing structural behavior patterns and maximum values.