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.     

Digital twin-based analysis of volumetric error mapping procedures

The evaluation of the volumetric accuracy of a machine tool is an open challenge in the industry, and a wide variety of technical solutions are available in the market and at research level. All solutions have advantages and disadvantages concerning which errors can be measured, the achievable uncertainty, the ease of implementation, possibility of machine integration and automation, the equipment cost and the machine occupation time, and it is not always straightforward which option to choose for each application. The need to ensure accuracy during the whole lifetime of the machine and the availability of monitoring systems developed following the Industry 4.0 trend are pushing the development of measurement systems that can be integrated in the machine to perform semi-automatic verification procedures that can be performed frequently by the machine user to monitor the condition of the machine. Calibrated artefact based calibration and verification solutions have an advantage in this field over laser based solutions in terms of cost and feasibility of machine integration, but they need to be optimized for each machine and customer requirements to achieve the required calibration uncertainty and minimize machine occupation time.This paper introduces a digital twin-based methodology to simulate all relevant effects in an artefact-based machine tool calibration procedure, from the machine itself with its expected error ranges, to the artefact geometry and uncertainty, artefact positions in the workspace, probe uncertainty, compensation model, etc. By parameterizing all relevant variables in the design of the calibration procedure, this simulation methodology can be used to analyse the effect of each design variable on the error mapping uncertainty, which is of great help in adapting the procedure to each specific machine and user requirements. The simulation methodology and the analysis possibilities are illustrated by applying it on a 3-axis milling machine tool.     

Designing optical glasses by machine learning coupled with a genetic algorithm

Engineering new glass compositions have experienced a sturdy tendency to move forward from (educated) trial-and-error to data- and simulation-driven strategies. In this work, we developed a computer program that combines data-driven predictive models (in this case, neural networks) with a genetic algorithm to design glass compositions with desired combinations of properties. First, we induced predictive models for the glass transition temperature (T_g) using a dataset of 45,302 compositions with 39 different chemical elements, and for the refractive index (n_d) using a dataset of 41,225 compositions with 38 different chemical elements. Then, we searched for relevant glass compositions using a genetic algorithm informed by a design trend of glasses having high n_d (1.7 or more) and low T_g (500 °C or less). Two candidate compositions suggested by the combined algorithms were selected and produced in the laboratory. These compositions are significantly different from those in the datasets used to induce the predictive models, showing that the used method is indeed capable of exploration. Both glasses met the constraints of the work, which supports the proposed framework. Therefore, this new tool can be immediately used for accelerating the design of new glasses. These results are a stepping stone in the pathway of machine learning-guided design of novel glasses.     

Pressure-induced transparency of MgO,Al2O3, AlN,and cBN ceramics at room temperature

The in situ axial X-ray diffraction patterns of four ceramic powder samples (MgO, Al₂O₃, AlN, and cBN) that were compressed in a diamond anvil cell under uniaxial non-hydrostatic conditions were recorded. The microscopic deviatoric stress as a function of the pressure was determined from the X-ray diffraction peak broadening analysis: the curves increased approximately linearly with the pressure at the initial compression stage and then levelled off under further compression. Pressure-induced transparency was observed in all of the samples under compression, and the pressure at the turning point on the curves of the microscopic deviatoric stress versus pressure corresponded to the pressure at which the samples became transparent. Analysis of the microstructural features of the pressure-induced transparent samples indicated that the compression caused the grains to fracture, and the broken grains bonded with each other. We demonstrated that the ceramics’ pressure-induced transparency was a process during which the grains were squeezed and broken, the pores were close between the grains, and the broken grains were re-bonded under compression.     

Identifying catalyst layer compositions of proton exchange membrane fuel cells through machine-learning-based approach

Membrane electrode assembly (MEA) is considered a key component of a proton exchange membrane fuel cell (PEMFC). However, developing a new MEA to meet desired properties, such as operation under low-humidity conditions without a humidifier, is a time- and cost-consuming process. This study employs a machine-learning-based approach using K-nearest neighbor (KNN) and neural networks (NN) in the MEA development process by identifying a suitable catalyst layer (CL) recipe in MEA. Minimum redundancy maximum relevance and principal component analysis were implemented to specify the most important predictor and reduce the data dimension. The number of predictors was found to play an essential role in the accuracy of the KNN and NN models although the predictors have self-correlations. The KNN model with a K of 7 was found to minimize the model loss with a loss of 11.9%. The NN model constructed by three corresponding hidden layers with nine, eight, and nine nodes can achieve the lowest error of 0.1293 for the Pt catalyst and 0.031 for PVA as a good additive blending in the CL of the MEA. However, even if the error is low, the prediction of PVA seems to be inaccurate, regardless of the model structure. Therefore, the KNN model is more appropriate for CL recipe prediction.     

A thermal perspective of flash sintering: The effect of AC current ramp rate on microstructure evolution

In flash sintering experiments, the thermal history of the sample is key to understanding the mechanisms underlying densification rate and final properties. By combining robust temperature measurements with current-ramp-rate control, this study examined the effects of the thermal profile on the flash sintering of yttria-stabilized zirconia, with experiments ranging from a few seconds to several hours. The final density was maximized at slower heating rates, although processes slower than a certain threshold led to grain growth. The amount of grain growth observed was comparable to a similar conventional thermal process. The bulk electrical conductivity correlated with the maximum temperature and cooling rate. The only property that exhibited behavior that could not be attributed to solely the thermal profile was the grain boundary conductivity, which was consistently higher than conventional in flash sintered samples. These results suggest that, during flash sintering, athermal electric field effects are relegated to the grain boundary.     

Influence of SiC microstructure on its corrosion behavior in molten FLiNaK salt

The influence of the microstructure on the corrosion rate of three monolithic SiC samples in FLiNaK salt at 900 °C for 250 h was studied. The SiC samples, labeled as SiC-1, SiC-2, and SiC-3, had corrosion rates of 0.137, 0.020, and 0.043 mg/cm²h, respectively. Compared with grain size and the presence of special grain boundaries (i.e., Σ3), the content of high-angle grain boundaries (HAGBs) appeared to have the strongest influence on the corrosion rate of SiC in FLiNaK salt, since the corrosion rate increased six times as the concentration of high-angle grain boundaries increased from 19 to 32% for SiC-2 and SiC-1, respectively. These results stress the importance of controlling the content of HAGBs during the production process of SiC.     

Understanding grain refining and anti Si-poisoning effect in Al-10Si/Al-5Nb-B system

Grain refinement is critical for fabricating high-quality Al-Si casting components in the application of automobile and aerospace industries,while the well-known Si-poisoning effect makes it difficult.Nbbased refiners offer an effective method to refine Al-Si casting alloys,but their anti Si-poisoning capability is far from being understood.In this work,the grain refining mechanism and the anti Si-poisoning effect in the Al-10 Si/Al-5 Nb-B system were systematically investigated by combining transmission electron microscope,first-principles calculations,and thermodynamic calculations.It is revealed that NbB₂provides the main nucleation site in the Al-10 Si ingot inoculated by 0.1 wt.%Nb Al-5 Nb-B refiner.The exposed Nb atoms on the(0001)NbB₂and(1-100)NbB₂surface can be substituted by Al to form(Al,Nb)B₂intermedia layers.In addition,a layer of NbAl₃-like compound(NbAl₃')can cover the surface of NbB₂with the orientation relation of(1-100)[11-20]NbB_2//(110)[110]NbAl₃'.Both of the(Al,Nb)B₂and NbAl₃'intermedia layers contribute to enhancing the nucleation potency of NbB₂particles.These discoveries provide fundamental insight to the grain refining mechanism of the Nb-B based refiners for Al-Si casting alloys and are expected to guide the future development of stronger refiners for Al-Si casting alloys.     

Synthesis,characterization and charge transport properties of Pr–Ni Co-doped SrFe2O4 spinel for high frequency devices applications

Ferrites are materials of interest due to their broad applications in high technological devices and a lot of research has been focused to synthesize new ferrites. In this regard, an effort has been devoted to synthesize spinel Pr–Ni co-substituted strontium ferrites with a nominal formula of Sr_1-xPr_xFe_2-yNi_yO₄ (0.0 ≤ x ≤ 0.1, 0.0 ≤ y ≤ 1.0). The cubic structure of pure and Pr–Ni co-substituted strontium ferrite samples calcinated at 1073 K for 3 h has been confirmed through X-ray diffraction (XRD). Average sizes of crystallites (18–25 nm) have been estimated from XRD analysis and nanometer particle sizes of synthesized ferrites have been further verified by scanning electron microscopy (SEM). SEM results have also shown that particles are mostly agglomerated and all the samples possess porosity. It has been observed that at 298 K, the values of resistivity (ρ) increase, while that of AC conductivity, dielectric loss, and dielectric constants decrease with increasing amounts of Pr³⁺ and Ni²⁺ ions. The values of dielectric parameters initially decrease with frequency and later become constant and can be explained on the basis of dielectric polarization. Electrochemical impedance spectroscopy (EIS) studies show that the charge transport phenomenon in ferrite materials is mainly controlled via grain boundaries. Overall, synthesized ferrite materials own enhanced resistivity values in the range of 1.38 × 10⁹–1.94 × 10⁹ Ω cm and minimum dielectric losses, which makes them suitable candidates for high frequency devices applications.