Multivariate Time Series (MTS) anomaly detection is critical for various applications. Yet, most existing methods rely on forecasting or reconstruction-based frameworks, which suffer from inherent uncertainties in handling complex MTS data. The recently emerging imputation-based anomaly detection leverages partial observations to reconstruct the masked values, thereby enhancing reconstruction stability and detection performance. However, in existing imputation-based methods, training on the masked data may lead to the omission on the global spatiotemporal distributional features of the MTS. Additionally, multiple masking strategies must be employed to ensure all data points have the opportunity to be reconstructed, resulting in repeated training and significant computational consumption. To address these limitations, this paper proposes ImConDM, a novel anomaly detection framework integrating imputation with conditional diffusion models. It trains a diffusion model on the complete training data and leverages the controllable sampling capabilities of diffusion models to perform conditional imputation guided by observed values, enabling stable and comprehensive MTS feature learning without retraining. Extensive experiments on six real-world MTS datasets demonstrate that ImConDM significantly outperforms eleven state-of-the-art baselines. Notably, compared with the second-best model, it achieves a 20.5% improvement in detection accuracy on high-dimensional datasets and reduces training time by at least 58%. The executable codes of the experiments with datasets and our algorithms are available at https://github.com/Labman-Wangjunjie/ImConDM.

Accurate prediction of both the Widmanstätten start (W_s) temperature and the transformation stasis requires a quantitative description of the energy barrier governing the growth of Widmanstätten ferrite. In this study, a concise model is developed by explicitly distinguishing the energy barriers associated with lengthening and thickening. The model adopts the lengthening barrier attributed to curvature and strain energies, and further incorporates the thickening barrier caused by strain energy, together with the diffusional dissipation of substitutional solute. The W_s temperature is predicted by the condition under which the energy barriers for both lengthening and thickening can be overcome, while transformation stasis occurs when the thickening barrier becomes insurmountable due to progressive carbon enrichment of untransformed austenite. The new model enables accurate prediction of the W_s temperatures across Fe-xC and Fe-0.1C-xMn/Ni/Si/Cr/Mo systems and the carbon enrichment in austenite at stasis in Fe-C-Mn and Fe-C-Mn-Si alloys.