Boosting AI Reliability with an FSM-Driven Streaming Inference Pipeline: An Industrial Case

Providing reliable predictive maintenance is a critical industrial AI service essential for ensuring the high availability of manufacturing devices. Existing deep-learning methods present competitive results on such tasks but lack a general service-oriented framework to capture complex dependencies in industrial IoT sensor data. While Transformer-based models show strong sequence modeling capabilities, their direct deployment as robust AI services faces significant bottlenecks. Specifically, streaming sensor data collected in real-world service environments often exhibits multi-scale temporal correlations driven by machine working principles. Besides, the datasets available for training time-to-failure predictive services are typically limited in size. These issues pose significant challenges for directly applying existing models as robust predictive services. To address these challenges, we propose MsFormer, a lightweight Multi-scale Transformer designed as a unified AI service model for reliable industrial predictive maintenance. MsFormer incorporates a Multi-scale Sampling (MS) module and a tailored position encoding mechanism to capture sequential correlations across multi-streaming service data. Additionally, to accommodate data-scarce service environments, MsFormer adopts a lightweight attention mechanism with straightforward pooling operations instead of self-attention. Extensive experiments on real-world datasets demonstrate that the proposed framework achieves significant performance improvements over state-of-the-art methods. Furthermore, MsFormer outperforms across industrial devices and operating conditions, demonstrating strong generalizability while maintaining a highly reliable Quality of Service (QoS).

Small defects in unfamiliar product categories can be difficult to distinguish from benign appearance variations in a global view. Additional reasoning over the same view may leave this ambiguity unresolved. We introduce IndusAgent, a Qwen3-VL-8B inspection policy trained through supervised fine-tuning and tool-augmented reinforcement learning for cross-category industrial anomaly detection. The policy selects among six tools for cropping, enhancement, measurement, within-image comparison, texture analysis, and external visual opinions from Qwen3-VL-Max, then integrates returned observations into a structured diagnosis. Indus-CoT provides 3,000 trajectories from 26 Real-IAD categories, generated with actual tool feedback and screened against annotations after teacher generation. GRPO optimizes an accuracy-gated objective that conditions localization, type, and tool rewards, including call costs, on final diagnostic correctness while retaining an independent format reward. Across five benchmarks, IndusAgent achieves 83.5% mean balanced accuracy, compared with 79.4% for direct Max inference under the common protocol. Across three training seeds, the five-benchmark mean balanced accuracy is 80.5% for a weight-matched ungated control and 83.5% for the gated policy. Evaluation uses disjoint product categories and a fixed defect vocabulary.

Existing video benchmarks evaluate action recognition on consumer videos, egocentric recordings, or simulated industrial environments. They do not test vision-language models under the visual and procedural conditions of real industrial CCTV, where workers appear as distant figures amid dust, steam, low light, glare, occlusion, and overlapping activities. We introduce STEELBENCH, a diagnostic benchmark for industrial surveillance that jointly evaluates per-worker activity recognition, safety-rule reasoning, and annotation provenance. SteelBench contains 1,345 densely annotated clips, curated from 149 hours of operational plant footage and 10,024 candidate clips using temporal deduplication, class balancing, and visibility-aware stratified sampling. Each clip includes dense per-worker action labels, PPE attributes, spatial context, and safety-rule annotations. Because model-assisted annotation can shape the labels later used for model evaluation, SteelBench includes a provenance-aware audit protocol. The protocol measures label influence, evaluates sensitivity to ground-truth provenance, and reports a human reference from expert-reviewed labels. Applying this audit, we find that unaudited VLM-sourced ground truth can inflate same-family model accuracy by up to 17 percentage points. Across nine VLMs from four architectural families, the best model reaches only 42.6% action accuracy, compared with an 84.6% human benchmark. Performance also fragments across recognition, robustness, calibration, and safety reasoning. Even when models predict the correct action, 37-58% of cases still yield incorrect safety judgments, and no model passes more than 2 of 5 diagnostic checks. The dataset is publicly available on Hugging Face.