Eng

An HPO (Hunter–Prey Optimizer)-optimized Bidirectional LSTM (HPO-BiLSTM) model is introduced to address the challenges in predicting gas concentration within coal mining working faces. This study aims to adaptively adjust the key hyperparameters (such as learning rate and number of hidden layer units) of the BiLSTM network through intelligent optimization algorithms. While the BiLSTM architecture inherently mitigates gradient vanishing and exploding problems through its gating mechanisms, the proposed HPO method focuses on addressing the inefficiency of manual parameter tuning and the risk of trapping in local optima that traditional methods encounter when dealing with nonlinear and non-stationary gas concentration time series. The experiment utilized the actual methane monitoring data from the 15117 working face of Jishazhuang Coal Mine in Jinzhong City, Shanxi Province (with a sampling interval of 2 min). The proposed HPO-BiLSTM model was compared with baseline models such as LSTM, BiLSTM, GA-BiLSTM, and PSO-BiLSTM in terms of performance. This study systematically compares the performance of LSTM, BiLSTM, and BiLSTM models optimized with GA, PSO, and HPO. Results demonstrate that all optimized models outperform the baselines, with HPO-BiLSTM achieving the best overall performance. It attained the lowest RMSE and highest R² across the training, validation, and test sets, showcasing superior fitting and generalization capabilities. Furthermore, HPO-BiLSTM converged to the lowest loss value (0.00062) in only 15 iterations, demonstrating significantly greater efficiency and stability than both GA-BiLSTM (loss 0.00072, 25 iterations) and PSO-BiLSTM (loss 0.00071, 30 iterations). The experiments confirm that the HPO algorithm effectively configures BiLSTM hyperparameters, mitigates overfitting, and provides a more accurate and robust solution for gas concentration prediction in coal mines.

The power-shift system employed in agricultural multi-range continuously variable transmissions (CVTs) features a complex structure and control logic, presenting significant challenges to the reliability of agricultural machinery. To enable timely detection of faults, constructing an intelligent fault diagnosis classifier to monitor the system’s health status is essential. Typically, fault samples utilized for classifier development originate from ideal bench tests, characterized by uniform patterns and limited diversity, thereby hindering the algorithm’s generalization capability. This study addresses this issue by proposing a generative adversarial network (GAN) model, integrated with a triple loss function and a novel generator architecture, to augment the fault dataset under laboratory conditions. The generator architecture comprises a variational autoencoder module and an oil pressure point attention mechanism, enabling the generation of diverse and fluctuating virtual samples. Building on this augmented dataset, a fault classifier based on one-dimensional ConvNeXt was developed. Experimental results indicate that the classifier achieves an accuracy of 99.73%. While classifier accuracy decreases with increasing noise levels, the GAN-generated dataset provides more comprehensive training, resulting in an accuracy approximately 3% higher than that achieved using the original dataset.

Securing mine sites is a challenging task due to the complexity of the infrastructure, the variety of physical and digital components, the distribution of assets and machineries, and the large number of stakeholders involved. Given the risks that are present in Tailings Storage Facilities (TSFs), mine operators are seeking technologies to accurately monitor the state of their dams. The latest developments implement evolutive monitoring and responsive risk management systems by adapting accurate Internet of Things technologies, automated mathematical model calculation to continually monitor the structural/geotechnical aspects of TSF, and a portfolio of innovative applications to support decision-making. Within this study, a comprehensive methodology is developed for assessing the environmental sustainability of a smart monitoring solution combining the life cycle assessment (LCA) method with the environmental risk assessment, which quantifies risk reduction potential. The use case scenario is identified based on real industrial data, also aligned with the common characteristics of tailing dams in Europe. Environmental sustainability of the smart monitoring solution is assessed through a cradle-to-grave LCA based on the ReCiPe 2016 (v1.1 Midpoint (H)) method. Monitoring impact alone is reduced primarily by the 40% reduction in monitoring visits, while the results show the environmental improvement of the TSF life cycle by 24% for CO₂-eq., as a step in-line with the EU’s long-term strategy for total decarbonisation in 2050, and Sustainable Development Goal 9 for Industry by the United Nations. Additionally, the 27% freshwater ecotoxicity reduction, 20% human toxicity (cancer) decrease, and the rest of the studied categories indicate an overall footprint improvement for the monitoring solution application on TSFs. The findings demonstrate clearly theoretical, practical and policy implications, not only for the benefit of such solutions for environmental protection, but also for the necessity of integrating risk in sustainability analysis approaches.