Enhancing predictive safety monitoring in longwall mining via interpretable multi-scale data fusion

Next-Generation AI Architecture for Real-Time Hazard Prediction and Safety Optimization in Mining Systems

The mining industry is a risky sphere of industry that is characterized by unstable geological conditions, the dangerous environment, and the active use of machinery. Traditional safety systems are based on manual surveillance and limits-like warnings, which are reactive in nature and cannot be used to mitigate the risk early enough. This paper suggests a next-generation AI system that can be used to predict hazards on-site and optimize safety in mining systems. The framework combines IoT-permitted environmental sensing, computer vision, and sophisticated machine learning models to continuously determine the level of gases, the structural integrity, machine well-being, and workers. The deep learning is also used in estimating non-destructive ore quality by using image-based mineral analysis, which facilitates effective resource management. Long short-term memory networks (LSTM) and Autoencoders are predictive models that learn and identify anomalies, predict possible failures, and calculate a dynamic risk index. The analytics dashboard is a cloud-driven solution with a hierarchy of alerts that allow proactive action to be taken. The accuracy in hazard detection and ore prediction is high in an experimental result and has a significant improvement in accuracy compared to traditional systems. The proposed architecture will contribute to the operational safety, efficiency, and sustainability and will lead to intelligent and autonomous mining ecosystems.

Interpretable RUL Prediction via Hybrid Deep Evidential clustering for Aero-Engine Health Monitoring

Remaining Useful Life (RUL) prediction is critical for predictive maintenance in safety-critical systems such as aerospace engines. While deep learning models achieve high predictive accuracy, they often lack interpretability and reliable uncertainty estimation. This paper proposes the Hybrid Deep Evidential Clustering (HDEC) framework to address both challenges. A CNN–LSTM–GRU backbone first extracts degradation features from multivariate time-series data. These features are then clustered using NN-EVCLUS, an evidential clustering approach based on Dempster–Shafer theory, which groups engines according to their degradation stage. A dedicated RUL predictor is trained for each cluster to enable specialized and interpretable predictions. Engines with uncertain cluster membership are handled through soft memberships, allowing RUL estimation as a weighted combination of cluster-specific predictors instead of hard assignment. Experiments on the NASA C-MAPSS dataset demonstrate that HDEC improves predictive performance while providing well-calibrated uncertainty estimates and interpretable degradation-regime assignments.

Multisensory Data-Driven Fault Prediction Model using Conformer-Attention Model

For large-scale industrial machine the advancement of Artificial Intelligence (AI) and sensor technology have transformed predictive maintenance approaches. To overcome these problems, this paper offers an AI-Driven Predictive Maintenance Framework that uses multisensory operational data for early defect detection and performance optimization. The raw input dataset fed to data exploration, cleaning and dimensionality reduction. Significant operational features are extracted from multisource sensor inputs via feature engineering and pattern recognition, while data imbalance is addressed with the SMOTE technique. The improved dataset is then sent through a hybrid Conformer-Attention model, which combines convolutional and transformer-style attention processes to capture both local and global temporal relationships. Finally, evaluation metrics are computed to ensure model’s dependability and performance which have the accuracy, precision, recall and F1-score of 99%. This AI-driven strategy increases machinery uptime, decreases maintenance costs and allows for proactive decision-making, all of which contribute to creation of intelligent and sustainable industrial systems.

An Intelligent predictive maintenance framework for fault prediction in industrial internet of things environments

A Time-Series AI Framework for Predictive Risk Assessment from Heterogeneous Sensor Data

This paper presents a time-series AI framework for predictive risk assessment using heterogeneous, irregularly sampled sensor data. The framework targets monitoring scenarios in which environmental covariates are available at high frequency, while the target variable is sparse, delayed, or obtainable only through laboratory analysis. The proposed pipeline integrates historical environmental data, IoT sensor streams, feature engineering, temporal windowing, domain alignment, and sequence-learning models within a unified forecasting process. The framework is evaluated in a precision livestock case study to predict the Total Bacterial Count in buffalo milk, a proxy indicator of microbiological risk. Sparse real TBC measurements are combined with Copernicus reanalysis data, local environmental sources, and farm IoT sensors. Recurrent and Transformer-based models are trained on sliding temporal windows and evaluated on both real and simulated TBC targets. Results show that datasource quality, feature representation, and look-back window length strongly affect predictive performance. Copernicus-based data and moderate temporal windows provide robust results, while the sparsity of real microbiological observations remains the main limiting factor. The proposed framework supports the transition from retrospective model training to sensor-based operational inference for early risk assessment.

Data-Driven Intelligent Analysis System for Monitoring and Anomaly Detection in Hydrogen Refueling Station

Hydrogen refueling station (HRS) requires continuous safety monitoring, yet conventional management relies largely on periodic inspection and manual oversight, limiting proactive risk mitigation. This study presents a data-driven intelligent analysis platform for real-time monitoring and anomaly detection of HRS safety data, including pressure, temperature, and flow-rate measurements from compressors, storage tanks, and dispensers. The platform integrates data collection adapters, a time-series database, and machine learning-based diagnostic modules (regression, clustering, and classification) into a unified reference software framework. For anomaly detection, an unsupervised LSTM-Variational Autoencoder trained on normal operating data is combined with DBSCAN-based clustering and a Mann–Kendall trend test to jointly identify point anomalies and pattern-level drifts, addressing the scarcity of labeled abnormal data in HRS environments. A continual learning mechanism further adapts detection thresholds to gradual and abrupt pattern changes without full retraining. The system was deployed and validated at BAM’s demonstration hydrogen refueling station in Germany, integrated with a remote safety-monitoring system and confirmed through performance testing, demonstrating reliable, proactive hydrogen safety management.