TokEye: 通过离线自监督学习快速提取波动时间序列信号:从融合诊断到生物声学
A general extractor for coherent patterns across time-frequency measurements
AI总结:
TokEye通过离线自监督学习从多种传感器数据中快速提取波动时间序列信号,用于等离子体波动测量与实时控制。
摘要:
下一代融合设施如ITER面临"数据洪流",每天生成数百万字节的多诊断信号,挑战手动分析。我们提出一种"信号优先"的自监督框架,用于从高噪声时间频率数据中自动提取相干和瞬态模式,适用于各种传感器。我们还开发了一种通用方法和工具,通过在多通道信号处理中使用非线性最优技术,结合快速神经网络替代品,在快速磁学、电子旋磁发射、二氧化碳干涉仪和束发射光谱测量(DIII-D)中提取相干、近相干和瞬态模式,用于等离子体波动测量。结果在DIII-D、TJ-II和非融合光谱图数据上测试。该框架的推理延迟为0.5秒,能够实现实时模式识别和大规模自动数据库生成,用于先进等离子体控制。仓库地址为https://github.com/PlasmaControl/TokEye。
英文摘要:
Scientific discovery increasingly depends on finding meaningful patterns within volumes of sensor data too large for manual inspection. Existing time-frequency event extractors are often engineered or trained on manually labeled examples for each instrument, which can be laborious and difficult to adapt to new environments. To address this, we introduce TokEye, a reference-free method that learns a general criterion for coherent structure from heterogeneous fusion measurements. A model developed under this method, without retraining, can extract signals from various other fields including marine bioacoustics and wideband radar. It recovers 82.5\% of expert-annotated stellarator signals, detects 78\% of dolphin whistles, and identifies radar events with 81.5\% average precision across six benchmarks, while processing full experimental spectrograms in under one second on a GPU. This transfer across unrelated sensors and physical systems reveals common exploitable structure in time-frequency measurements and establishes a scalable foundation for automated scientific signal discovery.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。