Home /Research /SyntheFormer: A multivariate variable-length time series data-based parallel Transformer model for explainable quality predicting and anomaly tracing

LEARNING📊 0 citations

SyntheFormer: A multivariate variable-length time series data-based parallel Transformer model for explainable quality predicting and anomaly tracing

Jiewu Leng, Xiaofeng Zhu, Jiahe Li, Zean Liu, Yuanfa Dong, Xueliang Zhou, Changhui Liu, Shuai Zheng, Chao Zhang, Qiang Liu, Xin Chen

Robotics and Computer-Integrated Manufacturing · 2026

Keywords

time seriesTransformerquality predictionanomaly tracingexplainable AI

SyntheFormer: A multivariate variable-length time series data-based parallel Transformer model for explainable quality predicting and anomaly tracing

Keywords

Related papers

Parallel Differentiable Reachability for Learning and Planning with Certified Neural Dynamics and Controllers

Artificial Intelligence enhanced smart welding islands: Foundation models revolutionizing manufacturing

A deep reinforcement learning and a dynamic graph neural network-based scheduling agent to control a multi-task robot

LLM Agent-driven Automated DFA Assessment with Fine-tuning and AAS-based RAG