Xiangang Cao

Fully mechanized mining equipment is core to the coal mining process. The selection process for this type of equipment is complex and heavily relies on experts’ experience for determining equipment parameters. This paper proposes a fully mechanized mining equipment parameter prediction model based on Extreme Gradient Boosting Regression Trees (XGBoost), which is developed based on the mapping relationships among geological parameters, fully mechanized mining face conditions, and the parameters of fully mechanized mining equipment. Feature selection is performed based on the feature importance ranking obtained through the Random Forest (RF) method, thereby reducing the model complexity. Different optimization algorithms are used to optimize the hyperparameters of XGBoost, and the results show that the Whale Optimization Algorithm (WOA) outperforms other algorithms in terms of convergence speed and optimization effectiveness. By comparing different prediction algorithms, it is found that the WOA-XGBoost model achieves higher prediction accuracy on the test set, with an average absolute error of 0.0458, root mean square error of 0.1610, and a coefficient of determination (R²) of 0.9451. Finally, a RF-WOA-XGBoost-based parameter prediction model for fully mechanized mining equipment is established, which is suitable for lightly inclined mining faces. This model reduces input complexity, improves the selection speed, minimizes reliance on experts, and ensures prediction accuracy, providing an effective reference for the parameter selection of fully mechanized mining equipment.

For multi-equipment maintenance of modern production equipment, the economic correlation and degradation uncertainty may lead to insufficient or excessive maintenance, increasing maintenance costs. This paper proposes a dynamic grouping maintenance method based on probabilistic remaining useful life (RUL) prediction for multiple equipment. Long short term memory (LSTM) is developed to predict the equipment probability RUL by the Variational Auto-Encoder (VAE) resampling. Then, the dynamic grouping maintenance model is constructed to minimize the maintenance cost rate under the known probabilistic RUL information. The gazelle optimization algorithm (GOA) is used to determine the optimal maintenance time for each equipment. To better verify the effectiveness of the proposed method, a numerical case with six wind turbines is introduced to analyse the performance of GOA. Moreover, the advantages of dynamic grouping maintenance is verified by comparing with independent maintenance, whose maintenance cost rate is reduced by 10.01%.

The requirements of high reliability for hybrid systems are urgent for engineers to maximize the system reliability under the limited cost budget. The cost constraint importance measure (CIM) is an important tool to achieve the local optimal solution by considering the relationship between constraint conditions and objective functions in the optimization problem. To better consider the contribution of the CIM, this paper considers three different cost function forms, including power type, trigonometric type, and exponential type. Combining the global search ability of the arithmetic optimization algorithm (AOA) with the local search ability of the CIM, a CIM-based arithmetic optimization algorithm (CIAOA) is developed to analyze the contribution of the CIM. Through the numerical experiments, the optimal system reliability and convergence generation of the CIAOA and AOA under different cost function forms are regarded as the indexes to analyze algorithm performance. The experimental results show that the average system reliability improvement percentages under power type, trigonometric type, and exponential cost constraint are 8.07%, 0.14%, and 0.53%, respectively, while the average convergence improvement percentages under three cost forms are 37.30%, 0.08%, and 1.66%, respectively. Therefore, the CIAOA performs the best under power cost constraints. Finally, a numerical example of a hybrid power vehicle system is introduced to analyze the contribution of the CIM under different cost functions by considering the reliability improvement rate in the optimal solution and the ranking of the CIM. The higher prioritization components in the two rankings are similar, which shows that the component with higher a CIM is selected to improve its reliability.

After a disaster, the recovery sequence of damaged bridges in a road–bridge transportation system greatly influences system restoration time and total economic loss. In this paper, the skew of recovery trajectory is introduced to evaluate the average restoration time, and the total economic loss is extended to consider the indirect loss, such as the energy consumption of detours or the emergency service fee. So, the post-disaster resilience optimization model is constructed by minimizing the total economic loss. The improved genetic algorithm is developed to obtain the optimal recovery scheme for damaged bridges by considering the recovery sequence and repair modes. The composition and influence factors of total economic loss are analyzed through three experiments. The experimental results show that the indirect loss accounts for approximately half of the economic loss, while the higher price of emergency service promotes the reduction of indirect loss using the expedited modes to repair damaged bridges. Moreover, to minimize the total economic loss, it is essential to design the optimal recovery scheme (repair sequence and repair mode) wisely to balance the conflicts between indirect loss and direct loss.

In nonrepairable multifunctional systems, the lost function of a component can be restored by the same function from another component; therefore, the activation mechanism of redundant functions illustrates that multifunctional systems have resilience features. This study evaluates the resilience of multifunctional systems and analyzes the properties of system resilience first. To determine the optimal start-up strategy, a resilience-oriented start-up strategy optimization model for onsite monitoring systems (OMSs) is established to maximize system resilience under a limited budget. In this study, real-time reliability is regarded as the system performance to evaluate the system resilience, and a two-stage local search based genetic algorithm (TLSGA) is proposed to solve the resilience optimization problem. The results of our numerical experiments show that the TLSGA can more effectively solve the problems for OMSs, with high function failure rates and low component failure rates compared with classical genetic algorithms under 48 systems. Moreover, the optimal combinations of unmanned aerial vehicles (UAVs) for an OMS under a limited budget shows that UAVs with a higher carrying capacity should be given priority for selection. Therefore, this study provides an effective solution for determining the optimal start-up strategy to maximize the resilience of OMSs, which is beneficial for OMS configuration.

Shearer-cutting units are important parts of coal production. However, they have high fault frequency, and their maintenance activities are costly and time-consuming. Coal enterprises urgently need an effective fault analysis method for shearer-cutting units. To solve this problem, an integrated importance measure (IIM) is introduced into the fault tree analysis method to identify the weakest links of shearer-cutting units. This paper develops an IIM-based fault tree analysis method to determine the key faults in shearer-cutting units. Taking MG400/930-WD shearer in Yuhua Coal Mine as an example, through IIM ranking, bearing wear can be identified as a key fault cause. To verify the effectiveness of the proposed method, the relative value distribution of four importance measures was analyzed by radial bar charts, and the accuracy of different rankings was evaluated by mean average precision. The results show that IIM can clearly distinguish the relative importance of bottom events, and the average accuracy of IIM ranking is 94.52%. Therefore, the proposed method can accurately and effectively identify key fault causes, and the limited resources should give priority to bottom events with higher IIM.