The paper introduces a framework that uses Large Language Models (LLMs) to generate synthetic time‑series data for manufacturing processes. By fine‑tuning pre‑trained LLMs on manufacturing instructions and applying Retrieval Augmented Generation (RAG), the method enhances data diversity and realism. Evaluation against traditional models such as ARIMA and LSTMs shows that the LLM‑driven approach produces higher‑quality synthetic data, better capturing temporal dependencies and improving downstream anomaly detection performance.
arXiv:2512.07624v2 Announce Type: replace Abstract: Process Model Forecasting (PMF) aims to predict how the control-flow structure of a process evolves over time by modeling the temporal dynamics of...
arXiv:2608. 06223v1 Announce Type: new Abstract: While deep learning models, particularly transformer-based architectures, have shown impressive performance in time series forecasting, the application of retrieval-augmented generation (RAG) in this domain remains limited.
arXiv:2607. 00720v1 Announce Type: cross Abstract: Despite the increasing sophistication of industrial AI systems, the ability to reliably detect subtle and noisy anomalies in complex time series data remains a critical yet unresolved challenge.
The paper presents a two‑stage multivariate monitoring framework for high‑dimensional, temporally dependent data from end‑of‑line testing in automotive manufacturing. Stage one cleans and aligns the data, while stage two applies nonlinear dimensionality reduction and a control‑chart‑based anomaly detection procedure that can operate in unsupervised or supervised modes. Applied to Ford Motor Company production data, the framework outperforms the existing model, raising accuracy from 0.50 to 0.625, recall from 0.30 to 1.00, and F1 score from 0.429 to 0.769.
Timer‑M1 is a pretrained multivariate time‑series foundation model that learns with primitives for zero‑shot forecasting. It uses a primitive‑based data synthesis and pretraining pipeline to generate series with shared temporal and relational patterns, assembling them into multivariate samples with distinct channel roles. The model employs gated two‑dimensional Transformer blocks that dynamically allocate cross‑variate attention, achieving top performance on several large‑scale forecasting benchmarks.
The paper introduces SiamSA-PPM, a self‑supervised framework that augments event logs for predictive process monitoring by generating realistic trace variants using control‑flow semantics and frequent behavioral patterns. It combines Siamese learning with statistically grounded data augmentation to learn generalizable prefix representations without requiring labeled data. Experiments on diverse real‑world logs show that SiamSA-PPM matches or outperforms state‑of‑the‑art baselines in next‑activity and final‑outcome prediction tasks.
While deep learning models, particularly transformer-based architectures, have shown impressive performance in time series forecasting, the application of retrieval-augmented generation (RAG) in this domain remains limited. Since RAG has proven effective in enhancing the capabilities of large language models by incorporating relevant external information, retrieving similar time series sequences as references might also improve accuracy in time series forecasting tasks.
arXiv:2606. 11990v1 Announce Type: cross Abstract: Remaining Useful Life (RUL) prediction is essential for industrial predictive maintenance, yet many learning-based approaches rely on extensive feature engineering or large labeled datasets to train task-specific sequence models.
arXiv:2606. 07291v1 Announce Type: new Abstract: Multivariate time-series forecasting requires models to reason over temporal dynamics, cross-variable dependencies, and historical input-output correspondences.
arXiv:2606. 15172v1 Announce Type: new Abstract: Synthesizing realistic time series with generative models has wide-ranging applications in real-world scenarios.
arXiv:2608. 10120v1 Announce Type: new Abstract: Modern sequence models, from Transformers to State Space Models, have enabled powerful generative modeling across diverse domains, yet they are typically trained to predict what happens while treating when it happens as a secondary concern.
D-TAIA is a framework that adapts large language models for multi‑task predictive process monitoring, jointly predicting the next activity and remaining time of ongoing cases. It uses domain‑aware triplet loss pre‑training, FAISS‑based nearest‑neighbor retrieval for time estimation, and a TAIA inference strategy to preserve sequential reasoning while fine‑tuning a 10 M‑parameter backbone. Across four real‑world event logs, D‑TAIA achieves state‑of‑the‑art or competitive results compared to a fine‑tuned LLM and a recurrent neural network baseline, with ablation studies showing the effectiveness of NLP and computer‑vision techniques for this domain.