Accurate prediction of nonstationary multivariate time series remains a critical challenge in complex industrial systems such as iron ore sintering. In practice, pronounced concept drift compounded by significant label verification latency rapidly degrades the performance of offline-trained models. Existing methods based on static architectures or passive update strategies struggle to simultaneously extract multi-scale spatiotemporal features and overcome the stability-plasticity dilemma without immediate supervision. To address these limitations, a Drift-Aware Multi-Scale Dynamic Learning (DA-MSDL) framework is proposed to maintain robust multi-output predictive performance via online adaptive mechanisms on nonstationary data streams. The framework employs a multi-scale bi-branch convolutional network as its backbone to disentangle local fluctuations from long-term trends, thereby enhancing representational capacity for complex dynamic patterns. To circumvent the label latency bottleneck, DA-MSDL leverages Maximum Mean Discrepancy (MMD) for unsupervised drift detection. By quantifying online statistical deviations in feature distributions, DA-MSDL proactively triggers model adaptation prior to inference. Furthermore, a drift-severity-guided hierarchical fine-tuning strategy is developed. Supported by prioritized experience replay from a dynamic memory queue, this approach achieves rapid distribution alignment while effectively mitigating catastrophic forgetting. Long-horizon experiments on real-world industrial sintering data and a public benchmark dataset demonstrate that DA-MSDL consistently outperforms representative baselines under severe concept drift. Exhibiting strong cross-domain generalization and predictive stability, the proposed framework provides an effective online dynamic learning paradigm for quality monitoring in nonstationary environments.

翻译：非平稳多变量时间序列的精确预测仍然是复杂工业系统（如铁矿石烧结）中的关键挑战。在实际应用中，显著的概念漂移与严重的标签验证延迟共同导致离线训练模型的性能迅速退化。现有基于静态架构或被动更新策略的方法难以在没有即时监督的情况下同时提取多尺度时空特征并克服稳定性-可塑性困境。为解决这些局限，本文提出一种漂移感知多尺度动态学习框架（DA-MSDL），通过在线自适应机制维持非平稳数据流上的鲁棒多输出预测性能。该框架采用多尺度双分支卷积网络作为主干，以解耦局部波动与长期趋势，从而增强对复杂动态模式的表征能力。为规避标签延迟瓶颈，DA-MSDL利用最大均值差异（MMD）进行无监督漂移检测。通过量化特征分布的在线统计偏差，DA-MSDL在推理前主动触发模型自适应。此外，本文提出了一种漂移严重度引导的分层微调策略。在动态记忆队列的优先经验回放支持下，该方法实现了快速分布对齐，同时有效缓解灾难性遗忘。基于真实工业烧结数据与公开基准数据集的长期实验表明，DA-MSDL在严重概念漂移下始终优于代表性基线方法。该框架展现出强大的跨领域泛化能力与预测稳定性，为非平稳环境下的质量监测提供了有效的在线动态学习范式。