Towards On-Board Implementation of ML-Based Helicopter Weight Estimator

面向机载实现的基于机器学习的直升机重量估算器

Abstract: This paper focuses on the implementation of a novel supervised Machine Learning model for estimating helicopter weight during takeoff, utilizing extensive datasets from Airbus’s global in-service fleet. 摘要： 本文重点介绍了一种新型监督机器学习模型的实现，该模型利用来自空客全球在役机队的广泛数据集，用于估算直升机起飞时的重量。

The study details a learning assurance process aligned with the EASA concept paper for machine learning application, and with the on-going Eurocae ED-324. 该研究详细阐述了一个符合欧洲航空安全局（EASA）机器学习应用概念文件以及正在制定的 Eurocae ED-324 标准的学习保证流程。

We propose a set of Machine Learning Requirements, a Machine Learning Model Description, and its implementation for a long short-term memory recurrent neural network. 我们提出了一套机器学习需求、机器学习模型描述，以及针对长短期记忆（LSTM）循环神经网络的实现方案。

Finally, we verify the requirements on the implementation. Demonstrated on legacy avionics computers, the implementation is suitable for the deployment of the developed Machine Learning Model weight estimator on airborne targets for critical functions such as on-board alerting. 最后，我们对该实现的各项需求进行了验证。在传统航空电子计算机上的演示表明，该实现适用于将所开发的机器学习模型重量估算器部署到机载目标上，以支持机载警报等关键功能。

---

Journal reference: The 2026 Annual Forum and Technology Display (Forum 82), The Future of Vertical Flight (VFS), May 2026, Palm Beach Florida, USA. 期刊参考： 2026 年度论坛与技术展示（第 82 届论坛），垂直飞行未来（VFS），2026 年 5 月，美国佛罗里达州棕榈滩。