发表机构
LAAS（LAAS）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出DT4X+，通过改进符号回归损失和训练集构建，使故障诊断关系与ARR性质一致，提升可解释性和性能，实验验证其有效性。
AI 中文摘要
将基于模型和数据驱动的范式相结合，通过结合解析冗余关系（即基于模型诊断中用作诊断指标的输入-输出关系）的可解释性与学习技术的适应性，为故障诊断提供了强大的框架。DT4X是一种最新的诊断算法，利用符号回归生成多元关系，利用解析冗余关系的某些性质，并将其用作决策树中的分裂函数。然而，其符号回归过程仅优化每个节点上两个选定类别之间的分离，常常使其余类别碎片化，从而降低可解释性和诊断性能。本文介绍了DT4X+，这是DT4X的增强版本，它修改了训练集的构建和符号回归损失，使得表达式在分离目标类别的同时保持非目标类别的连贯性。由此产生的关系与ARR性质完全一致，并导致更具信息量的分裂、改进的鲁棒性以及在动态系统数据集上更好的性能。在多个基准系统上进行的实验证明了这种增强公式的益处。
英文摘要
The integration of model-based and data-driven paradigms provides a powerful framework for fault diagnosis by combining the interpretability of analytical redundancy relations, i.e., input-output relations that are used as diagnosis indicators in model-based diagnosis, with the adaptability of learning techniques. DT4X is a recent diagnosis algorithm that uses symbolic regression to generate multivariate relations leveraging some properties of analytical redundancy relations and uses them as split functions in a decision tree. However, its symbolic regression procedure optimizes only the separation between two selected classes at each node, often fragmenting the remaining classes and degrading both interpretability and diagnosis performance. This paper introduces DT4X+, an enhanced version of DT4X that modifies the construction of training sets and the symbolic-regression loss so that expressions separate the target classes while preserving the coherence of non-target classes. The resulting relations become fully consistent with ARR properties and lead to more informative splits, improved robustness, and better performance on dynamic-system datasets. Experiments conducted on several benchmark systems demonstrate the benefits of this enhanced formulation.
CommentsSubmission accepted to IFAC WC 2026 (waiting for publication)
Journal ref23rd IFAC World Congress (IFAC World Congress 2026), Aug 2026, Busan, South Korea
