Machine learning algorithm selection for windage alteration fault diagnosis of mine ventilation system

Machine learning algorithms have been widely used in mine fault diagnosis. The correct selection of the suitable algorithms is the key factor that affects the fault diagnosis. However, the impact of machine learning algorithms on the prediction performance of mine fault diagnosis models has not been fully evaluated. In this study, the windage alteration faults (WAFs) diagnosis models, which are based on K-nearest neighbor algorithm (KNN), multi-layer perceptron (MLP), support vector machine (SVM), and decision tree (DT), are constructed. Furthermore, the applicability of these four algorithms in the WAFs diagnosis is explored by a T-type ventilation network simulation experiment and the field empirical application research of Jinchuan No. 2 mine. The accuracy of the fault location diagnosis for the four models in both networks was 100%. In the simulation experiment, the mean absolute percentage error (MAPE) between the predicted values and the real values of the fault volume of the four models was 0.59%, 97.26%, 123.61%, and 8.78%, respectively. The MAPE for the field empirical application was 3.94%, 52.40%, 25.25%, and 7.15%, respectively. The results of the comprehensive evaluation of the fault location and fault volume diagnosis tests showed that the KNN model is the most suitable algorithm for the WAFs diagnosis, whereas the prediction performance of the DT model was the second-best. This study realizes the intelligent diagnosis of WAFs, and provides technical support for the realization of intelligent ventilation.     

Hydrogen supply scenarios for a climate neutral energy system in Germany

A climate neutral energy system in Germany will most likely require green hydrogen. Two important factors, that determine whether the hydrogen will be imported or produced locally from renewable energy are still uncertain though - the import price for green hydrogen and the upper limit for photovoltaic installations. To investigate the impact of these two factors, the authors calculate cost optimized climate neutral energy systems while varying the import price from 1.25 €/kg to 5 €/kg with unlimited import volume and the photovoltaic limit from 300 GW to unlimited. In all scenarios, hydrogen plays a significant role. At a medium import price of 3.75 €/kg and photovoltaic limits of 300–900 GW the hydrogen supply is around 1200 to 1300 TWh with import shares varying from 60 to 85%. In most scenarios the electrolysis profile is highly correlated with the photovoltaic power, which leads to full load hours of 1870 h–2770 h.     

Exploring the feasibility of green hydrogen production using excess energy from a country-scale 100% solar-wind renewable energy system

When planning large-scale 100% renewable energy systems (RES) for the year 2050, the system capacity is usually oversized for better supply-demand matching of electrical energy since solar and wind resources are highly intermittent. This causes excessive excess energy that is typically dissipated, curtailed, or sold directly. The public literature shows a lack of studies on the feasibility of using this excess for country-scale co-generation. This study presents the first investigation of utilizing this excess to generate green hydrogen gas. The concept is demonstrated for Jordan using three solar photovoltaic (PV), wind, and hybrid PV-wind RESs, all equipped with Lithium-Ion battery energy storage systems (ESSs), for hydrogen production using a polymer electrolyte membrane (PEM) system. The results show that the PV-based system has the highest demand-supply fraction (>99%). However, the wind-based system is more favorable economically, with installed RES, ESS, and PEM capacities of only 23.88 GW, 2542 GWh, and 20.66 GW. It also shows the highest hydrogen annual production rate (172.1 × 10³ tons) and the lowest hydrogen cost (1.082 USD/kg). The three systems were a better option than selling excess energy directly, where they ensure annual incomes up to 2.68 billion USD while having payback periods of as low as 1.78 years. Furthermore, the hydrogen cost does not exceed 2.03 USD/kg, which is significantly lower than the expected cost of hydrogen (3 USD/kg) produced using energy from fossil fuel-based systems in 2050.     

Comparison of co-current and counter-current flow in a bifunctional reactor containing ammonia synthesis and 2-butanol dehydrogenation to MEK

In this study, a multi-tubular thermally coupled packed bed reactor in which simultaneous production of ammonia and methyl ethyl ketone (MEK) takes place is simulated. The simulation results are presented in two co-current and counter-current flow modes. Based on this new configuration, the released heat from the ammonia synthesis reaction as an extremely exothermic reaction in the inner tube is employed to supply the required heat for the endothermic 2-butanol dehydrogenation reaction in the outer tube. On the other hand, MEK and hydrogen are produced by the dehydrogenation reaction of 2-butanol in the endothermic side, and the produced hydrogen is used to supply a part of the ammonia synthesis feed in the exothermic side. Thus, 30.72% and 31.88% of the required hydrogen for the ammonia synthesis are provided by the dehydrogenation reaction in the co-current and counter-current configurations, respectively. Also, according to the thermal coupling, the required cooler and furnace for the ammonia synthesis and 2-butanol dehydrogenation conventional plants are eliminated, respectively. As a result, operational costs, energy consumption and furnace emissions are considerably decreased. Finally, a sensitivity analysis and optimization are applied to study the effect of the main process parameters variation on the system performance and obtain the minimum hydrogen make-up flow rate, respectively.     

Transmission system restoration with co-optimization of repairs,load pickups,and generation dispatch

This paper studies the restoration of a transmission system after a significant disruption such as a natural disaster. It considers the co-optimization of repairs, load pickups, and generation dispatch to produce a sequencing of the repairs that minimizes the size of the blackout over time. The core of this process is a Restoration Ordering Problem (ROP), a non-convex mixed-integer nonlinear program that is outside the capabilities of existing solver technologies. To address this computational barrier, the paper examines two approximations of the power flow equations: The DC model and the recently proposed LPAC model. Systematic, large-scale testing indicates that the DC model is not sufficiently accurate for solving the ROP. In contrast, the LPAC power flow model, which captures line losses, reactive power, and voltage magnitudes, is sufficiently accurate to obtain restoration plans that can be converted into AC-feasible power flows. An experimental study also suggests that the LPAC model provides a robust and appealing tradeoff between accuracy and computational performance for solving the ROP.     

Parallel chaos optimization algorithm with migration and merging operation

Chaos optimization algorithm (COA) utilizes the chaotic maps to generate the pseudo-random sequences mapped as the decision variables for global optimization applications. A kind of parallel chaos optimization algorithm (PCOA) has been proposed in our former studies to improve COA. The salient feature of PCOA lies in its pseudo-parallel mechanism. However, all individuals in the PCOA search independently without utilizing the fitness and diversity information of the population. In view of the limitation of PCOA, a novel PCOA with migration and merging operation (denoted as MMO-PCOA) is proposed in this paper. Specifically, parallel individuals are randomly selected to be conducted migration and merging operation with the so far parallel solutions. Both migration and merging operation exchange information within population and produce new candidate individuals, which are different from those generated by stochastic chaotic sequences. Consequently, a good balance between exploration and exploitation can be achieved in the MMO-PCOA. The impacts of different one-dimensional maps and parallel numbers on the MMO-PCOA are also discussed. Benchmark functions and parameter identification problems are used to test the performance of the MMO-PCOA. Simulation results, compared with other optimization algorithms, show the superiority of the proposed MMO-PCOA algorithm.     

An unsupervised approach to generating generic summaries of documents

We present an optimization-based unsupervised approach to automatic document summarization. In the proposed approach, text summarization is modeled as a Boolean programming problem. This model generally attempts to optimize three properties, namely, (1) relevance: summary should contain informative textual units that are relevant to the user; (2) redundancy: summaries should not contain multiple textual units that convey the same information; and (3) length: summary is bounded in length. The approach proposed in this paper is applicable to both tasks: single- and multi-document summarization. In both tasks, documents are split into sentences in preprocessing. We select some salient sentences from document(s) to generate a summary. Finally, the summary is generated by threading all the selected sentences in the order that they appear in the original document(s). We implemented our model on multi-document summarization task. When comparing our methods to several existing summarization methods on an open DUC2005 and DUC2007 data sets, we found that our method improves the summarization results significantly. This is because, first, when extracting summary sentences, this method not only focuses on the relevance scores of sentences to the whole sentence collection, but also the topic representative of sentences. Second, when generating a summary, this method also deals with the problem of repetition of information. The methods were evaluated using ROUGE-1, ROUGE-2 and ROUGE-SU4 metrics. In this paper, we also demonstrate that the summarization result depends on the similarity measure. Results of the experiment showed that combination of symmetric and asymmetric similarity measures yields better result than their use separately.     

A simulation study of reduction kinetics for sponge iron production in a rotary hearth furnace

ABSTRACT

A mathematical model has been developed by coupling genetic algorithm (GA) with heat and material balance equations to estimate rate parameters and solid-phase evolution related to the reduction of iron ore-coal composite pellets in a multi-layer bed Rotary hearth Furnace (RHF). The present process involves treating iron ore-coal composite pellets in a crucible over the hearth in RHF. The various solid phases evolved at the end of the process are estimated experimentally, and are used in conjunction with the model to estimate rate parameters. The predicted apparent activation energy for the wustite reduction step is found to be lower than those of the reduction of higher oxides. The thermal efficiency is found to decrease significantly with an increase in the carbon content of the pellet. Thermal efficiency was also found to increase mildly up to three layers. Multilayer bed remains as a potential design parameter to increase thermal efficiency.     

A mathematical model for open pit mine production scheduling with Grade Engineering® and stockpiling

This paper presents the development and implementation of an innovative mixed integer programming based mathematical model for an open pit mining operation with Grade Engineering framework. Grade Engineering comprises a range of coarse-separation based pre-processing techniques that separate the desirable (i.e. high-grade) and undesirable (i.e. low-grade or uneconomic) materials and ensure the delivery of only selected quantity of high quality (or high-grade) material to energy, water, and cost-intensive processing plant. The model maximizes the net present value under a range of operational and processing constraints. Given that the proposed model is computationally complex, the authors employ a data pre-processing procedure and then evaluate the performance of the model at several practical instances using computation time, optimality gap, and the net present value as valid measures. In addition, a comparison of the proposed and traditional (without Grade Engineering) models reflects that the proposed model outperforms the traditional formulation.