Search

Coal is one of the main sources of human energy. In the process of coal mining, separating gangue from coal has great significance for environmental protection and energy conservation. The core problem in the separation of gangue is the recognition of coal and gangue. In this study, multispectral technology was used to identify gangue. First, set up a data acquisition system in the laboratory, and then collect spectral data. Coal and gangue spectral data were collected in 202 and 201 groups, respectively. Secondly, design a spectral data dimension reduction model called two-dimension autoencoder(2D-AE). Finally, Random Forest was used to recognize coal and gangue. Meanwhile, CART, KNN, SVM, and AdaBoost were also used for gangue identification. The experimental results show that the maximum average accuracy by 2D-AE combined with RF was the largest, which was 98.89%. Also, the accuracy of gangue recognition is different for spectral images of different wavelengths. This paper mainly studies the recognition of coal and gangue based on multispectral technology, which is of great significance for the next step of detecting gangue based on the technology.

Seepage and heat transfer in the carbonate reservoir under low-temperature tail water reinjection is a complex coupling process, which is an important basis for scientific and reasonable evaluation of geothermal resource sustainability. This study based on the tracer test of double-well reinjection for carbonate heat reservoir, a coupling model of seepage field and temperature field of fracture network is established by using the finite element software COMSOL. The uncertainty analysis is carried out to study the fluid-thermal coupling process of carbonate fracture under the condition of low-temperature tail water reinjection.The variation law of seepage field and temperature field of thermal reservoir under low-temperature geothermal tail water reinjection is revealed, The variation of measured temperature of thermal reservoir pumping side under different reinjection conditions is predicted. The results show that the dominant fracture channels between wells of the fractured heat reservoir in Xian county geothermal field play an important role in controlling the seepage heat transfer. Under the coupling action of the seepage field, pressure field and the temperature field of the heat reservoir, the low-temperature tail water reinjection forms a preferential flow along the dominant channels, which is one of the important factors to consider in the prediction of thermal breakthrough. Reinjection pressure, temperature and well spacing are the main factors for artificial control of geothermal production and reinjection system. In the pumping and reinjection system of Xian county geothermal field, under the conditions of 0.5 MPa reinjection pressure, 30 °C reinjection tail water temperature and 270 m spacing between pumping and reinjection wells, the heat reservoir temperature at the pumping side decreased by 1.5 °C in 100 years.

Background:Breast cancer is the second dangerous cancer in the world. How to identify breast cancer quickly and accurately is of great help to the treatment of breast cancer. Breast cancer data often contains more redundant information. Redundant information makes the breast cancer auxiliary diagnosis less accurate and time-consuming. Dimension reduction algorithm combined with machine learning can solve these problems well. Methods:This paper proposes the single-parameter decision-theoretic rough set (SPDTRS) combined with the probability neural network (PNN) model for breast cancer diagnosis. We structure fifteen models by combining five dimensionality reduction algorithms with three classification algorithms. We compared the accuracy and test time of fifteen models under different parameters or dimensions. We find that when the parameter value of SPDTRS is 2.5, the classification effect of SPDTRS combined with PNN is better. At this point, the number of 30 attributes of the original breast cancer data dropped to 12. Then the SPDTRS-PNN model is further optimized. We compared the accuracy and test time of the model under different SPREAD values in PNN, and established a better SPDTRS-PNN model.Result:We find the parameter value of SPDTRS is 2.5 and the SPREAD value is 0.75, the accuracy of the SPDTRS-PNN model training set is 99.25%, the accuracy of the test set is 97.04%, and the test time is 0.093s.Conclusion:The experimental results show that the SPDTRS-PNN model can improve the accuracy of breast cancer recognition, reduce the time required for diagnosis, and achieve rapid and accurate breast cancer diagnosis.

In order to meet the needs of high-altitude, long-endurance, high mobility, functional and economic requirement for the future unmanned aerial vehicle(UAV), advanced composite materials have been increasingly applied in UAVs at home and abroad, and even many all-composite UAVs are manufactured. However, there are still some gaps in the proportion and technical level of composite materials used in UAVs in China compared with foreign countries. The cost of composite parts is one of the main factors restricting its application. This paper introduces the development process of UAV at home and abroad, and summarizes the application of composite materials on UAVs. Some key technologies and development trends of UAV composite materials are proposed. Some questions and suggestions are raised on the application of domestic composite materials on drones. For accelerating the application of composite materials in UAV industry in China, it is necessary to design the composite structure based on the process feasibility and stability with introducing foreign automation technology to reduce composite structure cost, actively develop various liquid forming technology, bag vacuum only-out of autoclave(BVO-OoA) materials and technology, and improve the traditional moulding technology research.

Density-based spatial clustering of applications with noise (DBSCAN) is a typical kind of algorithm based on density clustering in unsupervised learning. It can cluster data of arbitrary shape and also identify noise samples in the dataset. However, an unavoidable defect of the DBSCAN algorithm exists since the clustering performance is quite sensitive to the parameter settings of MinPts and Eps, and there is no theory to guide the setting of its parameters. Therefore, a new method is proposed to optimize the DBSCAN parameters in this paper. Multi-verse optimizer algorithm, a special variable updating method with excellent optimization performance, is selected and improved for optimizing the parameters of DBSCAN, which not only can quickly find out the highest clustering accuracy of DBSCAN, but also find the interval of Eps corresponding to the highest accuracy. In order to search the range of Eps more quickly and efficiently, we design a new mechanism for the variable update of MVO. The experimental results show that the improved MVO is used to optimize DBSCAN, which not only can quickly find out its highest clustering accuracy but also can search the parameters of MinPts and Eps corresponding to the highest clustering accuracy efficiently.

Laser-induced fluorescence (LIF) technology is an advanced optical detection method, which has the advantages of fast, high precision and nondestructive testing, and is widely used in many fields. The general pattern recognition method for fluorescence spectral classification is highly dependent on pretreatment and dimension reduction. Specific pretreatment and dimension reduction methods are required for specific substances. Deep learning, especially the convolutional neural network (CNN), has the advantage of low dependence on data preprocessing and dimensionality reduction process, which makes it perform well in spectral classification. However, learning a useful CNN model for classification depends crucially on the expertise of parameter tuning and some ad hoc tricks, which is not suitable for chemometrics researchers. This paper presents a novel chemometrics tool for fluorescence spectra, principal component analysis network (PCANet), and more specifically a PCANet model with the optimized hyper-parameters (only optimized once). A two-stage cascaded PCANet model is constructed based on the liquor dataset, and the hyper-parameters are optimized and determined, which can make PCANet recognition model with the highest accuracy. Comparing the CNN model with two convolutional layers, the PCANet model is less affected by the size of the input image and the number of samples in the training set. At the same time, the performance of the two models on the mine water dataset is analyzed, and PCANet has higher recognition accuracy. That is to say, the PCANet is more accurate than CNN in fluorescence spectral classification, and its ability to expand application is stronger than that of the CNN model. The successful application of PCANet model with the optimized hyper-parameters (only optimized once) in the liquor dataset and the mine water dataset has important reference significance for the classification of fluorescence spectra of other substances in the future.

The aim of this work is to determine the thermal storage temperature of a deep thermal reservoir, which has a great significance for the effective utilization of geothermal resources. The temperature of the reservoir was estimated by the cation ratio geothermometer and SiO2 geothermometer methods. The results indicate that the K–Mg geothermometer is the best method of the cation ratio methods, with the calculated temperature of 108°C. The average value calculated by the SiO2 method was 107°C. The measured temperature of the GRY1 drilling water sample in the Cangxian arch belt was 108°C. Because the calculated results of the geothermometers were consistent with the measured value of the borehole water, the K–Mg and SiO2 geothermometers are suitable for the estimation of deep heat storage temperatures.

Exposed to thundercloud and downward leader, coupling with operation voltage, glow corona discharge could be ignited in the vicinity of the UHVDC transmission line, leading to space charge layer, which could influence subsequent upward leader process from ground wires and conductors. To investigate the effect of space charge on lightning shielding performance of UHVDC transmission line, based on charge simulation method and upstream element method, the numerical calculation model of space charge distribution of ±1100kV UHVDC transmission line under thundercloud and downward leader was established in this paper, combined with leader inception and propagation model. The space distribution of space charge was obtained and the effect of space charge on exposure arcs of ground wires was analyzed. Meanwhile, the effect of corona space charge on upward leader parameters of ground wires and conductors, such as leader length, leader current, and leader velocity, were discussed quantitatively and qualitatively. Results showed that space charge inhibited leader inception and propagation, and had a more inhibitory effect on ground wires. Therefore, considering space charge, the upward leader was more likely to generate from the conductors and finish the final jump process. Further investigations on the inhibitory effect of space charge were carried out using space potential distortion. Results in this paper could provide data support for lightning shielding analysis of the UHVDC transmission line.

This paper analyzes the strain stability during mining, which often causes a water inrush. Mining couses costant stress on the fault zone, which is a loading process on the system composed of fault material and surrounding medium. A cusp catastrophe model is presented and the necessary and sufficient conditions leading to fault systems are discussed. The fault zone is assumed to be planar and is a combination of two media: medium-1 is elastic-brittle or strain-hardening and medium-2 is strain-softening. The shear stress-strain constitutive model for the strain-softening medium is described by the Weibull’s distribution law. It was found that the instability of a fault system mainly relies on the ratio between the stiffness of medium1 to the post-peak stiffness of the strain-softening medium, and the homogeneity index of strain-softening medium and the bifurcation point, k ≤ 1, which is the turning point of the fault system from stability to potential instability. One can judge the occurrence of fault instability from this feature and regard the index D as a parameter, which reflects the precursory abnormality of a fault.

Short-term electric load forecasting plays a significant role in the safe and stable operation of the power system and power market transactions. In recent years, with the development of new energy sources, more and more sources have been integrated into the grid. This has posed a serious challenge to short-term electric load forecasting. Focusing on load series with non-linear and time-varying characteristics, an approach to short-term electric load forecasting using a “decomposition and ensemble” framework is proposed in this paper. The method is verified using hourly load data from Oslo and the surrounding areas of Norway. First, the load series is decomposed into five components by variational mode decomposition (VMD). Second, a support vector regression (SVR) forecasting model is established for the five components to predict the electric load components, and the grey wolf optimization (GWO) algorithm is used to optimize the cost and gamma parameters of SVR. Finally, the predicted values of the five components are superimposed to obtain the final electric load forecasting results. In this paper, the proposed method is compared with GWO-SVR without modal decomposition and using empirical mode decomposition (EMD) to test the impact of VMD on prediction. This paper also compares the proposed method with the SVR model using VMD and other optimization algorithms. The four evaluation indexes of the proposed method are optimal: MAE is 71.65 MW, MAPE is 1.41%, MSE is 10,461.32, and R2 is 0.9834. This indicates that the proposed method has a good application prospect for short-term electric load forecasting.

Multi-functional metasurface devices are of great importance for miniaturization and integration. Here we propose a novel approach to design dual-functional dielectric metasurface doublets based on the principle of Pancharatnam-Berry phase. The functionalities for the two operating wavelengths can be independently designed by adjusting the orientation angle of the nanofins in the upper layer and that in the lower layer, respectively. The functionality can be switched by simply changing the incident wavelength. The simulated results of the examples demonstrate that the designed dual-functional doublet works well as expected.

As the highest component of wind turbines, the blades are vulnerable to lightning damages. The existing calculation models either cannot give characteristics of lightning attachment point distributions on wind turbine blades or lack well-developed physical processes. Besides, the optimization of the blade lightning protection system design is short of the guidance of calculation results. Based on the self-consistent leader inception and propagation model, a calculation method for characteristics of lightning attachment point distributions on wind turbine blades during the development of the downward leader was proposed in this paper. The lightning strike probability of six typical locations on the 2MW wind turbine blade surface was calculated using the ratio of lightning collection area, and the maximum lightning current of tip shielding failure was defined as well. The prospective return stroke current amplitude, the downward leader original position and the blade rotational angle were taken into consideration as three independent random variables, of which the effects on distribution characteristics of lightning attachment points were also evaluated. Calculation results showed that the rotational angle significantly affected the maximum lightning current of tip shielding failure. The protection scope of the blade tip was strongly influenced by rotor orientations, while the probability of the blade tip being struck is as high as 91.13%, which is much higher than the probabilities of the other locations along the blade. What's more, the probability of lightning strike in the region far from the tip (40 meters) is about twice that of regions near the tip (20–30 meters). Compared with the actual wind farm fault statistics, the reason for the high probability being struck in the area away from the tip is mainly related to the downward lightning strike. The characteristics of lightning attachment point distributions on the wind turbine blade calculated in this paper could provide theoretical basis for the design and optimization of blade lightning protection system.

The wind power system has always focus on the problem of lightning protection of wind turbine blades. Because of the increase of the capacity of wind turbines, the effective height of the wind turbines and the length of the blades also increase a lot, and the problem of the lightning protection failure of the existing blade lightning protection system (LPS) against direct lightning strikes has become prominent as well. There is still short of an optimization design of the LPS which can not only meet engineering requirements but receive all the downward lightning leaders. In this paper, a design scheme of overlying conductors on both of the leading edge and the tailing edge outside the tip of the blade was proposed to solute the delamination damage of the blades. This design of LPS could reduce the vicinal electric field of the down conductors, and reduce the probability of the streamer discharge incept from the down conductor as well as the discharge incept outside the laminate. The experimental study on the lightning protection performance was carried out under lightning and switching impulse voltage. The experimental results showed that the overlying conductors can effectively receive the downward leader to protect the blade from being penetrated in its laying range, but the protection efficiency would decline sharply when the downward leader developed outside the laying range. The covering length of the conductors should be 12% of the total length of the wind turbine blade, which can reduce the lightning damage by 90% or above.

We introduce a type of shape-invariant rotating beam in linear media with harmonic potentials. This type of beam is constructed by superposing a series of properly selected Laguerre-Gaussian beams of different orders. During propagation, the beam is shape invariant, but the pattern rotates and its size varies periodically. The transverse position of the beam at the exit plane of a medium can be steered by tuning the input parameters, even if the transverse position at the entrance plane is fixed.

The application of non-contact on-line detection technology on outdoor overhead equipment monitoring in distribution network is useful to find the equipment defects and avoid the insulating breakdown. The infrared thermal imaging method, ultrasonic based discharge detection method, ultraviolet imaging discharge detection method and UHF based discharge detection method are commonly applied. However, according to the feedback from the field operation, these methods are not enough to meet the requirements of the equipment condition monitoring, limited by the characteristics of the detection technology or the device. For example, the infrared thermal imaging detection has been widely used in the detection of abnormal temperature rise of equipment, but it also needs to combine with reasonable inspection plan to improve the detection efficiency; ultrasonic based discharge detection can quickly diagnose the existence of defects, it is now on trial in the distribution equipment defect detection, but still need quantitative detection characteristics, to provide the effective basis for the defective equipment condition assessment; ultraviolet imaging discharge detection is mainly limited by the device cost and detection efficiency, it can be used to detect the important or the focused equipment; UHF based discharge detection can diagnose the discharge defects quickly, the UHF antenna array based technology can also be further studied for the automatic, accurate and efficient detection on distribution equipment. Therefore, in order to improve the power supply reliability of distribution system, it still need to continue to optimize the detection technology and improve the distribution equipment inspection strategy to further enhance detection accuracy and efficiency.

The aim of this research was to investigate the biodiesel production from Pongamia pinnata seed oil and dimethyl carbonate with an iron oxide nano-catalyzed transesterification reaction. A significant biodiesel yield (96%) was obtained with optimal operating conditions as the dimethyl carbonate to oil molar ratio (5:1), iron oxide nano-catalyst (50 mg% based on oil weight), agitation speed of 150 rpm and 60°C temperature for 5 h reaction time. The produced methyl esters from the transesterification process were confirmed to be almost identical to commercial standard biodiesel by thin layer chromatography. The produced methyl esters were analyzed by gas chromatography-mass spectrometry using an internal standard. Properties of methyl esters were characterized such as kinematic viscosity at 40°C, specific gravity at 25°C, flash point, cloud point, pour point, copper strip corrosion and acid value. The properties of the produced biodiesel were within the specifications of the American biodiesel standard, ASTM D6751-02. The results showed that all of tested reaction variables in this study had positive effects. In this research studied, a novel method has developed for production of biodiesel under mild conditions using DMC and iron oxide nano-catalyst. Iron oxide nano-catalyst could be potential candidate for use in the large-scale biodiesel production.