What does this research mean for the field?

A knowledge-guided symbolic regression framework utilizing Large Language Models can generate explicit formulas that predict the lift increment of high-lift devices with accuracy comparable to computational fluid dynamics but at a significantly reduced computational cost. Novelty: ClaimNovelty.METHODOLOGICAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

What question did this study set out to answer?

To establish an explicit, accurate mathematical model for predicting the lift increment of aircraft high-lift devices using a knowledge-guided symbolic regression framework driven by large language models.

September 14, 2026Engineering Applications of Computational Fluid MechanicsOpen Access

Explicit modelling of lift characteristics for high-lift devices based on knowledge-guided symbolic regression using large language model

View Full Paper

Ask AI

Bookmark

Authors

YWYiheng Wang KZKefeng Zheng CLChengpeng Liu

Discussion

Member takes

Overview

Computational modeling demonstrates accurate lift prediction in high-lift aircraft devices via language model-guided symbolic regression, highlighting massive reductions in simulation costs.

Key Points

To establish an explicit, accurate mathematical model for predicting the lift increment of aircraft high-lift devices using a knowledge-guided symbolic regression framework driven by large language models.
Identified critical geometric parameters governing high-lift device performance and generated aerodynamic training data via high-fidelity fluid simulations.
Extracted mathematical features from multimodal representations of simulation data and embedded them alongside domain physics knowledge into natural language prompts.
Employed large language models within an evolutionary search framework to iteratively design and refine explicit symbolic formulas.
Produced an explicit formula that achieved lower mean square error and greater structural simplicity than conventional symbolic regression baselines.
Achieved aerodynamic lift predictions within a deviation of less than 2% compared to experimental wind tunnel test measurements.
Matched the predictive fidelity of computational fluid dynamics simulations while drastically lowering the required computational budget.

Cite This Study

Wang et al. (2026) studied this question.

synapsesocial.com/papers/6aa7b3440926e14a848b20d2 https://doi.org/10.1080/19942060.2026.2728948

View Full Paper

Ask AI

Bookmark

September 14, 2026Engineering Applications of Computational Fluid MechanicsOpen Access

Explicit modelling of lift characteristics for high-lift devices based on knowledge-guided symbolic regression using large language model

View Full Paper

Ask AI

Bookmark

Authors

YWYiheng Wang KZKefeng Zheng CLChengpeng Liu

Discussion

Member takes

Overview

Computational modeling demonstrates accurate lift prediction in high-lift aircraft devices via language model-guided symbolic regression, highlighting massive reductions in simulation costs.

Key Points

To establish an explicit, accurate mathematical model for predicting the lift increment of aircraft high-lift devices using a knowledge-guided symbolic regression framework driven by large language models.
Identified critical geometric parameters governing high-lift device performance and generated aerodynamic training data via high-fidelity fluid simulations.
Extracted mathematical features from multimodal representations of simulation data and embedded them alongside domain physics knowledge into natural language prompts.
Employed large language models within an evolutionary search framework to iteratively design and refine explicit symbolic formulas.
Produced an explicit formula that achieved lower mean square error and greater structural simplicity than conventional symbolic regression baselines.
Achieved aerodynamic lift predictions within a deviation of less than 2% compared to experimental wind tunnel test measurements.
Matched the predictive fidelity of computational fluid dynamics simulations while drastically lowering the required computational budget.

Cite This Study

Wang et al. (2026) studied this question.

synapsesocial.com/papers/6aa7b3440926e14a848b20d2 https://doi.org/10.1080/19942060.2026.2728948

View Full Paper

Ask AI

Bookmark