This study addresses Industry 5.0's demand for human-machine collaboration and manufacturing resilience by developing machine learning models for rapid fault identification and adaptive personnel scheduling. When a production-line fault occurs, the proposed approach uses IIoT data to identify the fault category quickly, support targeted intervention, and facilitate the restoration of normal production. XGBoost achieved near-perfect fault identification accuracy in model evaluation and accuracy and recall of 1.0 in validation, significantly outperforming the Random Forest baseline. Analysis revealed that experienced operators increased product qualification rates by 15% but reduced output by 10% due to physical factors. Decision tree regression minimized scheduling errors with an MSE of 0.49 and an R2 of 0.83. These results demonstrate that integrating IIoT-driven rapid fault identification with intelligent staffing provides a practical basis for shortening the response cycle, improving recovery capability after disruptions, and strengthening the resilience of human-centric manufacturing systems.
Yaocong Yaocong Xie, Ning Wang· ICST Transactions on Scalabl...· 0 citations
The deployment of embodied agents in self-driving laboratories could accelerate scientific discovery, yet their reliability is constrained by the irreversible and safety-critical nature of chemical experiments. Progress is further hindered by scarce failure data and the lack of fine-grained evaluation protocols. To address these challenges, we introduce LabRobFail, a failure-centric framework for learning and evaluating robotic failure analysis in chemical laboratories. LabRobFail-Sim injects controllable failures at the control, physics, and semantic levels, enabling the construction of LabRobFail-Data, which contains over 20,000 trajectories across 70+ task scenarios, five failure categories, and 11 fine-grained failure types. LabRobFail-Bench evaluates six capabilities spanning task understanding, failure detection, temporal localization, severity assessment, failure classification, and actionable correction. We further develop LabRobFail-VLM, a domain-specialized vision-language model that generates structured failure diagnoses and recovery instructions. On seen environments, it achieves 90.83% failure-detection accuracy and 77.21% temporal-localization accuracy, substantially outperforming general-purpose VLMs. When integrated as a real-time supervisor, it improves downstream task success rates by 4-16 percentage points, demonstrating the value of fine-grained failure understanding for closed-loop recovery and reliable laboratory autonomy. Our code and data are available at https://github.com/Su-ISE-2001/SciRobo
Haobo Wang, Baoli Sun, Anqi Zou et al.· 0 citations