Parameter Optimization Scheme Research Articles

Optimizing energy consumption in post-combustion CO2 capture at an NGCC power plant: A simulation-based approach

Abstract Approach
This study aims to optimize the energy consumption in post-combustion carbon capture processes at a Natural Gas Combined Cycle (NGCC) power plant to address the challenges associated with steam extraction from NGCC power plants and explore non-condensable energy requirements by leveraging heat integration and alternative solvent compositions. The research used simulations with commercially available software and literature-derived data to address the challenges of high energy consumption in such processes. Emphasis is placed on optimizing the solvent composition and implementing advanced heat optimization strategies to reduce the energy consumption. Four scenarios with different solvent compositions were investigated using monoethanolamine (MEA) and aqueous piperazine (PZ). The results show that the process parameter optimization and heat optimization strategies can result in

Quantitative Analysis of High-Price Rice Adulteration Based on Near-Infrared Spectroscopy Combined with Chemometrics.

Near-infrared spectroscopy (NIRS) holds significant promise in detecting food adulteration due to its non-destructive, simple, and user-friendly properties. This study employed NIRS in conjunction with chemometrics to estimate the content of low-price rice flours (Nanjing, Songjing, Jiangxi silk, Yunhui) blended with high-price rice (Wuchang and Thai fragrant). Partial least squares regression (PLSR), support vector regression (SVR), and back-propagation neural network (BPNN) models were deployed to analyze the spectral data of adulterated samples and assess the degree of contamination. Various preprocessing techniques, parameter optimization strategies, and wavelength selection methods were employed to enhance model accuracy. With correlation coefficients exceeding 87%, the BPNN models exhibited high accuracy in estimating adulteration levels in high-price rice. The SPXY-SG-BPNN, SPXY-MMN-BPNN, KS-SNV-BPNN, and SPXY-SG-BPNN models showcased exceptional performance in discerning mixed Wuchang japonica, Thai fragrant indica, and Thai fragrant Yunhui rice. As shown above, NIRS demonstrated its potential as a rapid, non-destructive method for detecting low-price rice in premium rice blends. Future studies should be performed to concentrate on enhancing the models' versatility and practical applicability.

Comparative Evaluation of Evapotranspiration and Optimization Schemes for Green Roof Runoff Simulations Using HYDRUS-1D

The use of green roofs, a low-impact development practice, can be an effective means of reducing direct runoff in urban centers. Green roof modeling can enable efficient design by preliminarily grasping the behavior of the green roof system according to specific configurations. In this study, we aimed to find appropriate evapotranspiration and parameter optimization schemes for HYDRUS-1D, a commonly used modeling tool for green roofs. Comparative studies of this sort in the context of green roof runoff modeling have not been conducted previously and are important in guiding users to overcome the difficulties of choosing the right numerical schemes for an accurate prediction of runoff from a green roof. As a study site, the Portland Building Ecoroof in Portland, Oregon, USA, was chosen, as green roof configurations and observed data for climate and runoff were available. From the simulation results of the runoff volume, the Blaney–Criddle method, which was considered an alternative, was found to be appropriate for calculating evapotranspiration from a green roof (R2 = 0.82) relative to the Hargreaves method built in HYDRUS-1D (R2 = 0.46). In addition, this study showed that the optimization method using the harmony search algorithm, which was proposed as an alternative optimizer, was better (R2 = 0.95) than that of the HYDRUS-1D’s own optimization module (R2 = 0.82) in calibrating HYDRUS-1D for green roof runoff. The findings are thought to be useful in guiding modelers who are considering using HYDRUS-1D for green roof runoff simulations.

Maximizing machining efficiency and quality in AA7075/Gr/B4C HMMCs through advanced DS-EDM parameter optimization strategies

Abstract Hybrid Metal Matrix Composites (HMMC) offer improved mechanical properties crucial for various industrial applications. However, machining these composites via traditional methods is arduous due to their inherent hardness and abrasive nature. The optimization of the Die-Sinking Electrical Discharge Machining (DS-EDM) process presents a viable solution to overcome these machining challenges and unlock the full potential of HMMCs. Despite the potential benefits of HMMCs, the lack of optimized machining strategies hampers their widespread adoption in industrial applications. Traditional machining approaches often result in excessive tool wear, poor surface finish, and suboptimal material removal rates (MRR) when applied to HMMCs. Additionally, the complex interplay between DS-EDM process parameters and material properties necessitates a systematic investigation to identify optimal machining conditions. This study proposes a multi-step methodology to systematically optimize the DS-EDM process for machining HMMCs comprising AA7075 alloy, 5% of graphite (Gr), and 5% of boron carbide (B4C) particles, which is termed as (AA7075-GR-B4C). Beginning with the formulation of the composite material through stir casting, the research progresses to an L16 Orthogonal Array (L16-OA) based Design of Experiments (DoE) to investigate the effects of key process parameters on machining performance. Experimental testing is conducted to measure mechanical properties, followed by statistical analysis using Analysis of Variance (ANOVA) with Regression Analysis to identify significant factors influencing machining outcomes. Furthermore, an Artificial Neural Network with Black Widow Optimization (ANN-BWO) approach is employed to optimize machining performance metrics such as MRR, Surface Roughness Rate (SRR), and Tool Wear Rate (TWR). The Relative Error (RE) was estimated between experimental MRR (E-MRR), experimental TWR (E-TWR), experimental SRR (E-SRR), and predicted MRR (P-MRR), predicted TWR (P-TWR), predicted SRR (P-SRR) generated by ANN-BWO shows effectiveness of AA7075-GR-B4C.

Enhancing requirements-to-code traceability with GA-XWCoDe: Integrating XGBoost, Node2Vec, and genetic algorithms for improving model performance and stability

This study addresses the challenge of requirements-to-code traceability by proposing a novel model, Genetic Algorithm-XGBoost With Code Dependency (GA-XWCoDe), which integrates eXtreme Gradient Boosting (XGBoost) with a Node2Vec model-weighted code dependency strategy and genetic algorithms for parameter optimisation. XGBoost mitigates overfitting and enhances model stability, while Node2Vec improves prediction accuracy for low-confidence links. Genetic algorithms are employed to optimise model parameters efficiently, reducing the resource intensity of traditional methods. Experimental results show that GA-XWCoDe outperforms the state-of-the-art method TRAceability lInk cLassifier (TRAIL) by 17.44% and Deep Forest for Requirement traceability (DF4RT) by 33.36% in terms of average F1 performance across four datasets. It is significantly superior to all baseline methods at a confidence level of α¡0.01 and demonstrates exceptional performance and stability across various training data scales.

Evaluation of entropy-coupled multi-criteria decision-making methods for enhancing machinability

Optimizing machining parameters is crucial, enhancing machinability while maintaining high product quality standards. This study bridges a critical research gap by evaluating and comparing five Taguchi-based Multi-Criteria Decision Making (MCDM) techniques—Combined Compromised Solution (CoCoSo), Grey Relational Analysis (GRA), Multi-Objective Optimization Ratio Analysis (MOORA), Technique for Order Preference by Similarity to Ideal Solution (TOPSIS), and Complex Proportional Assessment (COPRAS)—coupled with the Entropy method to optimize machining parameters for enhancing machinability in turning medium carbon steel. The focus is on feed rate and cutting speed under dry and Minimum Quantity Lubrication (MQL) environments considering six critical machining responses: material removal rate, surface roughness, main cutting force, cutting temperature, cutting ratio, and tool life.The results reveal that MQL consistently improves machining performance, with COPRAS, TOPSIS, MOORA, and GRA converging on an optimal setting favoring an MQL environment, a 0.14 mm/rev feed rate, and a cutting speed of 137 m/min, whereas CoCoSo suggests a different optimal parameter setting. CoCoSo and GRA demonstrate the highest reliability, evidenced by minimal discrepancies between predicted and experimental results, with absolute percentage errors of 0.647 % and 0.659 %, respectively. The COPRAS method also shows strong predictive accuracy with a 5.573 % error, outperforming MOORA and TOPSIS. Spearman's rank correlation analysis reveals a high agreement between COPRAS, MOORA, and TOPSIS, with COPRAS emerging as a potential replacement for the latter in similar decision-making scenarios. SEM and EDX analyses confirm that MQL conditions reduce tool wear, enhance surface quality, and extend tool life compared to dry machining. This research provides insights into effective parameter optimization strategies for improving machinability and underscores the benefits of adopting MQL for sustainable manufacturing processes.

Power-aided probabilistic shaping parameter optimization for long-haul optical fiber transmission

A power-aided probabilistic shaping (PS) parameter optimization scheme is proposed to localize the optimal transmitting setup and maximize the transmission capacity in long-haul optical fiber transmission. Using a neural network and genetic algorithm (NNGA), the proposed scheme can select the optimal transmission parameter set, including the launching optical power (LOP) and three PS characteristics. We built a testbed using MATLAB and VPI to validate the proposed scheme. The proposed scheme was demonstrated in a dual-polarization coherent transmission system. The results show that the proposed scheme improves the generalized mutual information (GMI) by 0.3035 bits/symbol/pol and normalized GMI by 0.1022 in a 1000 km G.654E fiber transmission at 420-Gbit/s, compared to a traditional MB-based PS technique. The signal-to-noise ratio (SNR) achieves a gain of 1.003 dB, which validates the outperformance of the proposed scheme.

Unfolding multilevel agglomerative strategies for SVM classification: a case study in discriminating spectrally similar land covers

ABSTRACT In remote sensing applications, image classification algorithms normally require parameter optimization strategies to adapt to the complexities of the data and determine the model’s parameters for optimal performance. However, a unique set of hyper-parameters is generally chosen, without acknowledging the presence of subsets of classes that exhibit different levels of spectral similarity. A model used to distinguish between well-separable classes might not be optimal for delineating other classes. This study explores a classification method that extends the standard One-Against-One (OAO) and One-Against-All (OAA) strategies for Support Vector Machines (SVMs), based on agglomerative hierarchical clustering of spectrally-similar classes. The main objective is to provide additional classification scenarios where more detailed per-class analyses can be performed, rather than simple comparisons of global accuracies, particularly for hard-to-distinguish classes. Clusters of classes closely located in the feature space are initially classified using an OAA strategy, while each cluster undergoes further subdivision using an OAO approach. This strategy aims to identify the most effective sequence for incorporating subgroups of classes into the tuning process. The experimental results indicate that the proposed method can be efficiently applied to classify remote sensing data, producing varying levels of enhancement in per-class accuracies at each stage of the agglomerative process.

Runoff Prediction of Tunxi Basin under Projected Climate Changes Based on Lumped Hydrological Models with Various Model Parameter Optimization Strategies

Runoff is greatly influenced by changes in climate conditions. Predicting runoff and analyzing its variations under future climates are crucial for ensuring water security, managing water resources effectively, and promoting sustainable development within the catchment area. As the key step in runoff modeling, the calibration of hydrological model parameters plays an important role in models’ performance. Identifying an efficient and reliable optimization algorithm and objective function continues to be a significant challenge in applying hydrological models. This study selected new algorithms, including the strategic random search (SRS) and sparrow search algorithm (SSA) used in hydrology, gold rush optimizer (GRO) and snow ablation optimizer (SAO) not used in hydrology, and classical algorithms, i.e., shuffling complex evolution (SCE-UA) and particle swarm optimization (PSO), to calibrate the two-parameter monthly water balance model (TWBM), abcd, and HYMOD model under the four objective functions of the Kling–Gupta efficiency (KGE) variant based on knowable moments (KMoments) and considering the high and low flows (HiLo) for monthly runoff simulation and future runoff prediction in Tunxi basin, China. Furthermore, the identified algorithm and objective function scenario with the best performance were applied for runoff prediction under climate change projections. The results show that the abcd model has the best performance, followed by the HYMOD and TWBM models, and the rank of model stability is abcd > TWBM > HYMOD with the change of algorithms, objective functions, and contributing calibration years in the history period. The KMoments based on KGE can play a positive role in the model calibration, while the effect of adding the HiLo is unstable. The SRS algorithm exhibits a faster, more stable, and more efficient search than the others in hydrological model calibration. The runoff obtained from the optimal model showed a decrease in the future monthly runoff compared to the reference period under all SSP scenarios. In addition, the distribution of monthly runoff changed, with the monthly maximum runoff changing from June to May. Decreases in the monthly simulated runoff mainly occurred from February to July (10.9–56.1%). These findings may be helpful for the determination of model parameter calibration strategies, thus improving the accuracy and efficiency of hydrological modeling for runoff prediction.

Unraveling the interrelation between process parameters and defects to enhance the strength of laser additively manufactured CuZrAlTi bulk metallic glass

Laser powder bed fusion (LPBF) enables the production of large and intricately shaped bulk metallic glasses (BMGs); however, the current strength of LPBF-fabricated BMGs is significantly lower than their cast counterparts due to defects generated during the LPBF process in the as-built BMGs. In this study, considering the viscosity characteristics of BMG melts and their impact on melt pool characteristics, we investigated the relationship between LPBF parameters, structural characteristics, and defects in a selected Cu45Zr45Al6Ti4 BMG. Our findings revealed a transition of the melt pool from conduction mode to keyhole mode and subsequently to extended mode with increasing laser power. Furthermore, we explored how melt pool characteristics influence defects such as pores, heat affected zone (HAZ), and crystalline phase in the as-built Cu45Zr45Al6Ti4 BMG. Under optimized LPBF parameters, we successfully fabricated nearly fully amorphous Cu45Zr45Al6Ti4 BMG samples with high density (>99%) and absence of cracks. The printed samples exhibited a compressive strength of 1839 MPa comparable to their cast counterparts while achieving an impressive tensile strength value of 920 MPa, currently the highest reported for CuZr-based BMGs. This study enhances our understanding of the intrinsic relationship between LPBF parameters, melt pool characteristics, defects, and mechanical properties of LPBF-fabricated BMGs while providing a new parameter optimization strategy for reducing defects and achieving high strength in BMGs.

Effect of grit blasting on fatigue behavior of 2024-T3 aero Al alloy

Aiming at the removal of native oxide film on 2024-T3 Al alloy before plasma electrolytic oxidation, the methods to reduce the fatigue damage caused by grit blasting are explored. Effects of the grit size and pressure on surface roughness, residual compressive stress (RCS), and fatigue life of the Al alloy are studied. Increasing grit size and pressure leads to the increase in the surface roughness and RCS. Based on the theorem of momentum and tool cutting principle, mechanism of the grits on the craters and RCS is revealed. It is found that the angularness of the small-sized grit results in the formation of long scratches. The grit with high kinetic energy induces the large craters and high RCS. The craters are the primary fatigue crack initiation source. Moreover, the craters with long scratch and large height lead to the premature fatigue failure of the grit blasted specimens. However, Fatigue behavior is insignificantly affected by the RCS. The results provide new insights into the fatigue deterioration mechanism and life optimization of the grit blasted samples. Consequently, a parameter optimization scheme for the fatigue life of the grit blasted Al alloy is proposed.

Multi-Objective Parameter Optimization Strategy of Rheological Instability and Power Dissipation for Molybdenum Alloy Based on Genetic Algorithm

Because of the limited performance of the core material of heat pipe reactor, the cooling effect of nuclear power source is restricted. Molybdenum alloy with excellent comprehensive performance has been a popular core material. To improve the performance of the molybdenum alloy hot forming process, the rheological instability and power dissipation of recrystallized molybdenum alloys are studied by orthogonal arrays L16 with three factors and four levels in this paper. Considering the experimental temperature, strain rate and true strain, the rheological instability and power dissipation are optimized based on a genetic algorithm (GA), with optimal process parameters of recrystallized molybdenum alloys obtained as follows by taking the rheological instability and power dissipation as the objectives. The experimental temperature is 792.424 ℃, the strain rate is 0.01 s-1, the true strain is 0.1N, the rheological instability is 0.23336, and the power dissipation is 0.6832. The rheological instability is increased by 21.79% and the power dissipation is decreased by 64.95% compared with that in the experiment (the experimental temperature is 650 ℃, the strain rate is 0.01 s-1, and the true strain is 0.1N in the experiment with similar parameters in the orthogonal arrays).

Light-mediated biosynthesis of size-tuned silver nanoparticles using Saccharomyces cerevisiae extract

Bio-based production of silver nanoparticles represents a sustainable alternative to commercially applied physicochemical manufacturing approaches and provides qualitatively highly valuable nanomaterials due to their narrow size dispersity, high stability and biocompatibility with broad application potentials. The intrinsic features of nanoparticles depend on size and shape, whereby the controlled synthesis is a challenging necessity. In the present study, the biosynthesis of size-tuned silver nanoparticles based on cell-free extracts of Saccharomyces cerevisiae DSM 1333 was investigated. Single parameter optimization strategies in phases of cultivation, extraction, and synthesis were performed to modify the nanoparticle scale and yield. Visible light was exploited as a tool in nanoparticle production. The influence of white light on the biosynthesis of silver nanoparticles was determined by using novel LED systems with the exposition of varying irradiation intensities and simultaneous performance of control experiments in the dark. Characterization of the resulting nanomaterials by spectrophotometric analysis, dynamic light scattering, scanning electron microscopy, and energy dispersive X-ray spectroscopy, revealed spherical silver nanoparticles with controlled, light-mediated size shifts in markedly increased quantities. Matching of irradiated and non-irradiated reaction mixtures mirrored the enormous functionality of photon input and the high sensitivity of the biosynthesis process. The silver nanoparticle yields increased by more than 90% with irradiation at 1.0±0.2mWcm-2\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$1.0 \\pm 0.2\ ext{ mW }{\ ext{cm}}^{-2}$$\\end{document} and the reduction of particle dimensions was achieved with significant shifts of size-specific absorption maxima from 440 to 410 nm, corresponding to particle sizes of 130 nm and 100 nm, respectively. White light emerged as an excellent tool for nano-manufacturing with advantageous effects for modulating unique particle properties.Graphical abstract

OSSEFS: An online semi-supervised ensemble fuzzy system for data streams learning with missing values

The incompleteness of data samples in data streams always affects the performance of learning model. In order to learn data streams with missing values from features and a large amount of unlabeled data, this paper proposes a semi-supervised ensemble algorithm based on evolving fuzzy systems (EFS) named OSSEFS. Aiming at missing values, a fuzzy rule based online imputation strategy is designed to improve the data feature integrity. Aiming at unlabeled data, a new ensemble fuzzy system architecture is proposed to fully utilize both labeled and unlabeled data implicit information to predict data labels accurately. In addition, an online rule parameters optimization strategy is proposed to achieve adaptive adjustment of rule distribution. Thanks to the above strategies, OSSEFS can perform well in data environments containing missing values and unlabeled data. Comparative experimental results on multiple datasets show that OSSEFS outperforms the classical semi-supervised regression algorithms.

Optimization of governor parameters for transient process of hydropower system with two turbine units sharing a super long headrace tunnel

AbstractThe governor parameters affect the stability and regulation quality of hydropower system with two turbine units sharing a super long headrace tunnel (SLHT). To improve the transient process of hydropower system, this study investigates the optimization of governor parameters. First, the model of hydropower system with two turbine units sharing an SLHT is established. Second, the optimization scheme of governor parameters for transient process of hydropower system is designed by genetic algorithm. The mathematical formulation of genetic algorithm is illuminated. The implementation procedure of genetic algorithm is illustrated. Then, the optimization results of governor parameters by genetic algorithm are analyzed by illustrating the regulation quality of hydropower system under two operating conditions. Finally, the effect of asymmetrical factors on optimal governor parameters is revealed. The asymmetrical layout of bifurcated penstocks, asymmetrical layout of turbine units, and asymmetrical load disturbances are considered. The results indicate that the objective function of hydropower system is composed of the dynamic indexes for frequency oscillations of two turbine units and water level oscillation in surge tank. The fitness function evolves in the direction that makes the regulation quality of hydropower system become better. Under the symmetrical or asymmetrical bifurcated penstocks, turbine units, and load disturbances, the optimal parameters of governors are asymmetrical. The regulation quality of hydropower system under the governor parameters of genetic algorithm is obviously better than that under the governor parameters of Stein formula. The optimal governor parameters are directly affected by the asymmetrical factors of hydropower system. With the increase of the flow inertia of one bifurcated penstock, the optimal parameters of the other governor become greater.

Parametric optimization scheme of energy dissipation and shock absorption for prefabricated concrete frame

The prefabricated concrete frame structure system has advantages such as short construction period and good seismic performance, but its deformation and energy dissipation capacity are poor under earthquake action, making it prone to damage. By improving the analysis and simulation functions of existing finite element analysis for prefabricated structures, the engineering applicability of the analysis algorithm has been improved. Then, a finite element model has been established for collaborative optimization, and a parameterized optimization scheme that meets the seismic reduction requirements has been obtained. The results show that the optimization method proposed in the study has a better effect in seeking the minimum cost, and meets the design requirements of the specification. The optimization scheme of prefabricated concrete frames designed by the research institute based on finite element analysis can efficiently optimize various parameters, greatly improving the structure energy dissipation and seismic performance.

Prediction and explanation of debris flow velocity based on multi-strategy fusion Stacking ensemble learning model

The debris flow velocity fundamentally determines its intensity, thereby rendering its prediction a crucial aspect of disaster prevention and control strategies. However, accurate velocity prediction has consistently posed significant challenges due to the intricate interplay of various influential factors. To address the limitations of existing models, an explainable multi-strategy fusion of Stacking ensemble learning is proposed. Initially, an improved snake optimization (ISO) algorithm is employed to adjust parameters within the model’s learners. Benchmark function comparison tests are then conducted to validate the reliability of the ISO algorithm. Subsequently, a learner selection method based on predictive performance and degree of difference is established to facilitate the selection of basic learners and meta-learners. This leads to the construction of the Stacking ensemble learning model, achieved through the integration of parameter optimization strategies from the improved swarm intelligence algorithm strategy, the error weighting strategy, and the decomposition strategy. To assess the model, a case study of the Jiangjiagou Gulley debris flow is undertaken, focusing on the prediction of the debris flow velocity. The results demonstrate high predictive accuracy, with RMSE, MAE, and MAPE values of 0.19, 0.17, and 2.46% respectively. Furthermore, under the SHAP framework, global and local explanations of the predictions are provided. Through feature importance analysis, the bed slope gradient is identified as the most crucial feature in the velocity prediction of the Jiangjiagou Gulley debris flow. Coupling effects and contributions of input features to the debris flow velocity prediction are further analyzed and explained through feature interaction analysis and single sample analysis. This study not only provides a new method for debris flow velocity prediction but also provides guiding suggestions for debris flow monitoring and control.

Adaptive Low-Rank Tensor Estimation Model Based Multichannel Weak Fault Detection for Bearings.

Multichannel signals contain an abundance of fault characteristic information on equipment and show greater potential for weak fault characteristics extraction and early fault detection. However, how to effectively utilize the advantages of multichannel signals with their information richness while eliminating interference components caused by strong background noise and information redundancy to achieve accurate extraction of fault characteristics is still challenging for mechanical fault diagnosis based on multichannel signals. To address this issue, an effective weak fault detection framework for multichannel signals is proposed in this paper. Firstly, the advantages of a tensor on characterizing fault information were displayed, and the low-rank property of multichannel fault signals in a tensor domain is revealed through tensor singular value decomposition. Secondly, to tackle weak fault characteristics extraction from multichannel signals under strong background noise, an adaptive threshold function is introduced, and an adaptive low-rank tensor estimation model is constructed. Thirdly, to further improve the accurate estimation of weak fault characteristics from multichannel signals, a new sparsity metric-oriented parameter optimization strategy is provided for the adaptive low-rank tensor estimation model. Finally, an effective multichannel weak fault detection framework is formed for rolling bearings. Multichannel data from the repeatable simulation, the publicly available XJTU-SY whole lifetime datasets and an accelerated fatigue test of rolling bearings are used to validate the effectiveness and practicality of the proposed method. Excellent results are obtained in multichannel weak fault detection with strong background noise, especially for early fault detection.

Sealing performance analysis of pressure controller in pressure core sampling for seafloor drill

In order to improve the working reliability of pressure controller in the pressure core sampling for the seafloor drill, the challenges faced by the pressure controller in the working phase are analyzed. The working parameters of Y-ring on the pressure-retaining performance are analyzed. The optimization scheme of the working parameters for Y-ring is obtained and verified by sea trial. The conclusions are as follows: The gap extrusion degree of Y-ring is proportional to the working pressure. When the working pressure exceeds 20 MPa, the increase rate of the maximum contact stress increases. Under the condition that the friction coefficient is 0.1–0.4, the safety margin of the maximum contact stress is proportional to the friction coefficient. When the friction coefficient increases from 0.4 to 0.5, the safety margin decreases. Under the condition that the interference is 0.66–0.76 mm, the growth rate of the maximum Mises stress is slow. when the interference is 0.7 and 0.76 mm, the safety margin decreases. When the extrusion gap is 0.4–0.6 mm, the increase trend of safety margin is more obvious. When the extrusion gap is 0.6 mm, the growth rate of the maximum Mise stress increases. The success rate of the sealing cap installation is about 80%.

Dynamic prediction of high-temperature points in longwall gobs under a multi-field coupling framework

Spontaneous coal combustion (SCC) in longwall gobs is a serious disaster and requires prediction tools to accurately and reliably predict the temperature in gobs, but currently, there has been a lack of simple and efficient predictors. To address this issue, the temperature distributions in a longwall gob under different mining state parameters were simulated using a multi-fields coupled model. The temperature distribution and the mining state parameters were extracted to serve as input variables for prediction. Two machine learning models, integrating parameter optimization and ensemble learning strategies, respectively, were proposed to establish the functional relationships between the dynamic change boundary temperature and the maximum temperature in the gob. The results show that these two models have good prediction accuracy on the high-temperature points in longwall gobs, indicating that the ensemble learning has improved prediction accuracy. There is a positive correlation between the number of measuring points and the prediction accuracy, and three measurement points at the key locations can deliver reliable predictive performance.