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.     

A model of PEMFC-battery system to evaluate inner operating status and energy consumption under different energy management strategies

A hybrid system with jointed battery and PEMFC is popular and of great potential in New Energy Vehicle (NEV) application. However, reliability and efficiency remain to be improved for commercial products. To reflect the complicated physics inside the proton exchange membrane fuel cell (PEMFC), the PEMFC model consisting of inner muti-physics process and other accessories was built, then a complete hybrid system was established when a matched battery, DC/DC, regenerative braking were taken into consideration. Based on the above model, the stack state and system performance under standard cycle for heavy duty vehicle-CWTVC were obtained. According to the simulation results, fuel cell states such as pressure, water content and voltage suffers severe oscillation with external load, especially in the highway cycle. Membrane electrode assembly (MEA) suffers from pressure impact with average value of more than 24 kPa in highway cycle. In the aspect of relative humidity, the PEMFC stack is most threatened in road cycle. As for the hybrid system, its efficiency and state of charge (SOC) fluctuation perform worst in urban cycle and road cycle respectively, while its highest efficiency occurs in road test. Operating mode of fuel cell has influence on hybrid system. When 3-level mode of fuel cell output was applied, the efficiency increased to its peak value at medium level of 28 kW and then declined gradually. H₂ consumption had an opposite trend compared to efficiency. In the aspect of battery SOC, it declines in operating process and its fluctuations decreases when medium level got bigger. The 3-level mode and 4-level mode were compared using this model. It can be concluded that although 3-level mode performs slightly better in hybrid system efficiency, H₂ consumption, pressure impact, it does not have absolute advantage over 4-level mode in other indicators.     

Study on inhomogeneous cooling behavior of extruded profile with unequal and large thicknesses during quenching using thermo-mechanical coupling model

The interfacial heat transfer coefficient between hot profile surface and cooling water was determined by using inverse heat conduction model combined with end quenching experiment. Then, a Deform-3D thermo-mechanical coupling model for simulating the on-line water quenching of extruded profile with unequal and large thicknesses was developed. The temperature field, residual stress field and distortion of profile during quenching were investigated systematically. The results show that heat transfer coefficient increases as water flow rate increases. The peak heat transfer coefficient with higher water flow rates appears at lower interface temperatures. The temperature distribution across the cross-section of profile during quenching is severe nonuniform and the maximum temperature difference is 300 °C at quenching time of 3.49 s. The temperature difference through the thickness of different parts of profile first increases sharply to a maximum value, and then gradually decreases. The temperature gradient increases obviously with the increase of thickness of parts. After quenching, there exist large residual stresses on the inner side of joints of profile and the two ends of part with thickness of 10 mm. The profile presents a twisting-type distortion across the cross-section under non-uniform cooling and the maximum twisting angle during quenching is 2.78°.     

Comfort design and optimization of direct expansion multi-connected radiant air conditioning based on 3D flow field simulation

The air conditioning method based on radiation heat exchange has the characteristics of small vertical temperature gradient, high thermal comfort and energy saving, and has become a hot spot of attention. The Fluent numerical simulation, the experiment in this paper studies the direct expansion multi-line radiant air conditioner under the artificially simulated climate environment in winter heating, summer cooling and dehumidification. The temperature difference of the radiation + fresh air mode at the same time indoors under heating conditions is less than 2.5 °C, and the time to reach the indoor set temperature of 24 °C is about 2–3 h. Under cooling conditions, the temperature difference of the radiation + fresh air mode at the same time in the room is about 0.5–2 °C, and the time to reach the indoor set temperature of 26 °C is about 1–3 h. In the fresh air mode, the indoor temperature difference and response time at the same time are slightly larger than the radiation + fresh air mode. The freezing and dehumidification effect of fresh air is obvious, the moisture content of dehumidifying fresh air is between 6.3 and 10.5 g/kg, and the dehumidification efficiency can reach 50%. Under the same artificial simulated climate environment, the consumption of the three modes is not much different. When the outdoor temperature in heating conditions is higher than 9 °C, the fresh air mode can get better, and the radiation + fresh air mode can achieve better comfort when running indoors under various conditions.     

A mechanism informed neural network for predicting machining deformation of annular parts

Controlling machining deformation of annular parts is crucial for ensuring the performance of high value products and equipment. For example, during manufacturing of critical parts in aircrafts and spacecrafts, accurate prediction of machining deformation is the basis for guiding the formulation of deformation control strategies. However, due to the complexity of the machining deformation of annular parts, existing methods still have limitations in accurate prediction. To this end, this paper proposes a mechanism informed neural network (MINN) to predict machining deformation of annular parts. MINN is realized by establishing the dual sub-networks structure and using enhanced loss functions with the consideration of the deformation mechanism model characteristics of annular parts. The deformation was decomposed into the axisymmetric portion and the non-axisymmetric portion according to the deformation superposition principle, and modeled separately based on the thin-shell theory and Fourier series. Experiment results showed that the proposed method could predict the machining deformation of annular parts more accurately and stably with a small amount of training data, compared with previous methods.     

铁基材料表面激光熔覆不锈钢涂层的研究进展

激光熔覆技术作为推动国家制造业升级的重要绿色制造和再制造技术,在航空航天、海工交通、冶金机械等重点领域具有广阔的应用前景。激光制造用粉末材料是影响该技术应用和发展的关键因素之一,其中铁基合金材料具有成本低、力学性能好、应用范围广等优势,特别是不锈钢体系的铁基合金因其良好的力学性能和优异的耐蚀性能而逐渐成为研究关注的焦点。全面综述了国内外在铁基材料表面激光熔覆不锈钢涂层的相关研究进展。根据显微组织的不同,目前采用激光熔覆技术制备的不锈钢涂层的类型主要有:奥氏体型不锈钢、马氏体型不锈钢、铁素体型不锈钢以及双相型不锈钢。重点综述了激光工艺参数(激光功率、扫描速度、熔覆方式等)、合金元素(Al、Ni、B、Mo等)、添加物(SiC、WC、VC、Cr3C2、Al2O3等陶瓷相)以及热处理(固溶处理、低温回火等)等因素对激光熔覆不锈钢涂层组织和性能的影响,主要包括对熔覆层的相组成、截面几何尺寸、稀释率、残余应力、力学性能、耐蚀性能等的影响规律及微观机制。同时,指出了目前在铁基材料表面激光熔覆不锈钢涂层领域中存在的主要问题及今后的发展方向。     

γ射线辐照和阳光照射对ZF6铅玻璃透光率的影响

通过实验研究ZF6铅玻璃在~(60)Co放射源相同剂量率不同累积剂量照射下透光率的变化规律。将辐照后的铅玻璃在室外阳光下、室内自然光下和不透光的抽屉中放置观察,发现阳光照射对铅玻璃辐照着色的恢复起着重要作用,在建立铅玻璃透光率随辐照时间变化的数学模型时,室内自然光对铅玻璃透光率的影响可忽略。实验数据验证了受辐照时铅玻璃透光率的变化与辐照时间符合指数函数关系。根据文献资料推导出铅玻璃透光率变化与光照时间为线性函数关系,但发现其与实验数据的符合程度较差,本文根据样条曲线插值法推导出铅玻璃透光率与光照时间为二次函数关系,与实验数据的符合效果较好。     

Role of zirconia phase transformation,interface processes,and Ta2O5 doping on the blistering phenomenon of molten glass in contact with zirconia-based refractories

Bubble formation and removal within the molten glass is an important issue in glass industry. Various sources of bubbles have been identified in glass manufacturing: decomposition of the glass components, air trapping, oxidation/reduction reactions, precipitation resulting from insufficient refining, etc. It has been demonstrated in a previous paper that the blistering phenomenon at the interface between a molten glass and a zirconia-based refractory can be ascribed to the oxygen semipermeability through the zirconia phase. The objective of this study is to clarify the role of temperature on the blistering process, and especially, below and above the phase transition temperature of zirconia (monoclinic/tetragonal transformation) and to evaluate the role of zirconia doping on the blistering level. The influence of the kinetics of the surface processes at the glass/refractory interface is emphasized. Quantitative measurement of the slight blistering ascribed to the so-called “redox shock” is also given.     

Oxidation of graphene-modified HfB2-SiC ceramics by supersonic dissociated air flow

The oxidation resistance of ultra-high-temperature ceramic material (HfB₂-30 vol%SiC)-2 vol%rGO (rGO: reduced graphene oxide) under long-term exposure (2000s) to a supersonic air flow has been studied. The ceramics were obtained by reactive hot pressing of HfB₂-(SiO₂-C)-rGO composite powder at a temperature of 1800°C (pressure 30 MPa, holding time 15 min, Ar). The surface temperature of graphene-modified ceramics under the influence of heating by high-enthalpy air flow (heat flow q reached 779 W·cm^–2) did not exceed 1700°C, which is 650–700°C less than for the HfB₂-30 vol%SiC baseline ceramics. This may be related to an increase in the efficiency of heat transfer from the sample to the water-cooled module, due to the higher thermal conductivity of the rGO-containing material. Thereby, a decrease in the material degradation degree has been noted, i.e. decrease in the recession rate and decrease in the total thickness of the oxidised ceramic layer by tenth. The peculiarities of the oxidised surface and near-surface region microstructure upon aerodynamic heating of the graphene-modified ceramic material, have been shown.     

Insight into t->m transition of MW treated 3Y-PSZ ceramics by grazing incidence X-ray diffraction

The influence of a microwave hybrid heat treatment (MHH) on the surface and in-depth mineralogical transformation of pre-sintered 3Y-PSZ was investigated. 3Y-PSZ samples were prepared by slip casting and sintered by conventional firing (1270 °C). Then, different MHH treatments from 5 to 15 min. at 1200 °C were applied to obtain a fully stabilized 3Y-TZP. The monoclinic fraction depth profiles in the first micrometres (up to 5) of thickness were investigated by means of the grazing incident X-ray diffraction technique (GIXRD). A good sintering degree with practically nil closed porosity and grain growth was achieved after MHH of 15 min. MHH increases the tetragonal phase content both in the surface and in-depth, reducing completely the monoclinic phase shell typically found after conventional sintering. A new parabolic model is proposed for the convoluted monoclinic fraction depth profile, which through the value of its horizontal asymptote allows the determination of the monoclinic shell thickness.