基于分态的煤矿瓦斯浓度预测模型的研究

由于影响瓦斯浓度变化的因素很多且内部关系复杂,传统的单一预测模型无法客观准确地反映其变化规律,导致预测精度较低。为有效提高瓦斯浓度预测精度,提出一种基于分态的预测模型。应用最大李雅普诺夫指数(Lyapunov指数)对瓦斯浓度时间序列的混沌特性进行识别,将其分为非混沌态和混沌态,接着分别采用改进的最小二乘支持向量机(LS-SVM)和基于径向基函数(Radial Basis Function,RBF)的神经网络进行建模和训练参数的优化,最终得到最佳预测模型并对瓦斯浓度时间序列进行预测。结果表明,分态预测模型有效提高了预测精度,降低了预测误差,用该方法可以更加客观准确地对瓦斯浓度进行预测。

Improved AVOA based on LSSVM for wind power prediction

Improving the prediction accuracy of wind power is an effective means to reduce the impact of wind power on power grid.Therefore,we proposed an improved African vulture optimization algorithm(AVOA)to realize the prediction model of multi-objective optimization least squares support vector machine(LSSVM).Firstly,the original wind power time series was decomposed into a certain number of intrinsic modal components(IMFs)using variational modal decomposition(VMD).Secondly,random numbers in population initialization were replaced by Tent chaotic mapping,multi-objective LSSVM optimization was introduced by AVOA improved by elitist non-dominated sorting and crowding operator,and then each component was predicted.Finally,Tent multi-objective AVOA-LSSVM(TMOALSSVM)method was used to sum each component to obtain the final prediction result.The simulation results show that the improved AVOA based on Tent chaotic mapping,the improved non-dominated sorting algorithm with elite strategy,and the improved crowding operator are the optimal models for single-objective and multi-objective prediction.Among them,TMOALSSVM model has the smallest average error of stroke power values in four seasons,which are 0.0694,0.0545 and 0.0211,respectively.The average value of DS statistics in the four seasons is 0.9902,and the statistical value is the largest.The proposed model effectively predicts four seasons of wind power values on lateral and longitudinal precision,and faster and more accurately finds the optimal solution on the current solution space sets,which proves that the method has a certain scientific significance in the development of wind power prediction technology.

Random noise attenuation by f–x spatial projection-based complex empirical mode decomposition predictive filtering

The frequency–space（f–x） empirical mode decomposition（EMD） denoising method has two limitations when applied to nonstationary seismic data. First, subtracting the first intrinsic mode function（IMF） results in signal damage and limited denoising. Second, decomposing the real and imaginary parts of complex data may lead to inconsistent decomposition numbers. Thus, we propose a new method named f–x spatial projection-based complex empirical mode decomposition（CEMD） prediction filtering. The proposed approach directly decomposes complex seismic data into a series of complex IMFs（CIMFs） using the spatial projection-based CEMD algorithm and then applies f–x predictive filtering to the stationary CIMFs to improve the signal-to-noise ratio. Synthetic and real data examples were used to demonstrate the performance of the new method in random noise attenuation and seismic signal preservation.

Studies on stand dynamic growth model for larch in Jilin in China

The stand growth and yield dynamic models for Larch in Jilin Province were developed based on the forest growth theories with the forest continuous inventory data. The results indicated that the developed models had high precision, and they could be used for the updating data of inventory of planning and designing and optimal decision of forest management.

An enhanced hybrid ensemble deep learning approach for forecasting daily PM_(2.5)

PM_(2.5) forecasting technology can provide a scientific and effective way to assist environmental governance and protect public health.To forecast PM_(2.5),an enhanced hybrid ensemble deep learning model is proposed in this research.The whole framework of the proposed model can be generalized as follows:the original PM_(2.5) series is decomposed into 8 sub-series with different frequency characteristics by variational mode decomposition(VMD);the long short-term memory(LSTM)network,echo state network(ESN),and temporal convolutional network(TCN)are applied for parallel forecasting for 8 different frequency PM_(2.5) sub-series;the gradient boosting decision tree(GBDT)is applied to assemble and reconstruct the forecasting results of LSTM,ESN and TCN.By comparing the forecasting data of the models over 3 PM_(2.5) series collected from Shenyang,Changsha and Shenzhen,the conclusions can be drawn that GBDT is a more effective method to integrate the forecasting result than traditional heuristic algorithms;MAE values of the proposed model on 3 PM_(2.5) series are 1.587,1.718 and 1.327μg/m3,respectively and the proposed model achieves more accurate results for all experiments than sixteen alternative forecasting models which contain three state-of-the-art models.

Species Transformation of Trace Elements and Their Distribution Prediction in Dyestuff Residue Incineration

The release of heavy metals from the combustion of hazardous wastes is an environmental issue of in-creasing concern.The species transformation characteristics of toxic heavy metals and their distribution are consid-ered to be a complex problem of mechanism.The behavior of hazardous dyestuff residue is investigated in a tubular furnace under the general condition of hazardous waste pyrolysis and gasfication.Data interpretation has been aided by parallel theoretical study based on a thermodynamic equilibrium model based on the principle of Gibbs free en-ergy minimization.The results show that Ni,Zn,Mn,and Cr are more enriched in dyestuff residue incineration than other heavy metals(Hg,As,and Se)subjected to volatilization.The thermodynamic model calculation is used for explaining the experiment data at 800℃ and analyzing species transformation of heavy metals.These results of species transformation are used to predict the distribution and emission characteristics of trace elements.Although most trace element predictions are validated by the measurements,cautions are in order due to the complexity of incineration systems.

High-Order Lateral Buckling Analysis of Submarine Pipeline Under Thermal Stress

It is of importance to study and predict the possible buckling of submarine pipeline under thermal stress in pipeline design.Since soil resistance is not strong enough to restrain the large deformation of pipeline,high-order buckling modes occur very easily.Analytical solutions to high-order buckling modes were obtained in this paper.The relationships between buckling temperature and the amplitude or the wavelength of buckling modes were established.Analytical solutions were obtained to predict the occurrence and consequence of in-service buckling of a heated pipeline in an oil field.The effects of temperature difference and properties of subsoil on buckling modes were investigated.The results show that buckling will occur once temperature difference exceeds safe temperature;high-order pipeline buckling occurs very easily;the larger the friction coefficients are,the safer the submarine pipeline will be.

TIME-SERIES MODELI NG AND FAULT FORECAST STUDY ON SPECTRAL ANALYSIS OF LUBRICATING OIL

The application of ti me-series modeling and forecasting method to the spectral analysis for lubricat ing oil of mechanical equipment is discussed. The AR model is used to perform a time-series modeling and forecasting analysis for the spectral analysis data co llected from aero-engines. In the oil condition monitoring field of mechanical equipment, the use of the method of time-series analysis has rarely been report ed. As indicated in the satisfactory example, a practical method for condition m onitoring and fault forecasting of mechanical equipment has been achieved.

Manganese potential mapping in western Guangxi-southeastern Yunnan(China) via spatial analysis and modal-adaptive prospectivity modeling

While the region of western Guangxi-southeastern Yunan, China, is known and considered prospective for manganese deposits, carrying out prospectivity mapping in this region is challenging due to the diversity of geological factors, the complexity of geological process and the asymmetry of geo-information. In this work, the manganese potential mapping for further exploration targeting is implemented via spatial analysis and modal-adaptive prospectivity modeling. On the basis of targeting criteria developed by the mineral system approach, the spatial analysis is leveraged to extract the predictor variables to identify features of the geological process. Specifically, a metallogenic field analysis approach is proposed to extract metallogenic information that quantifies the regional impacts of the synsedimentary faults and sedimentary basins. In the integration of the extracted predictor variables, a modal-adaptive prospectivity model is built, which allows to adapt different data availability and geological process. The resulting prospective areas of high potential not only correspond to the areas of known manganese deposits but also provide a number of favorable targets in the region for future mineral exploration.

Effective forecast of Northeast Pacific sea surface temperature based on a complementary ensemble empirical mode decomposition–support vector machine method

The sea surface temperature （SST） has substantial impacts on the climate; however, due to its highly nonlinear nature, evidently non-periodic and strongly stochastic properties, it is rather difficult to predict SST. Here, the authors combine the complementary ensemble empirical mode decomposition （CEEMD） and support vector machine （SVM） methods to predict SST. Extensive tests from several different aspects are presented to validate the effectiveness of the CEEMD-SVM method. The results suggest that the new method works well in forecasting Northeast Pacific SST at a 12-month lead time, with an average absolute error of approximately 0.3℃ and a correlation coefficient of 0.85. Moreover, no spring predictability barrier is observed in our experiments.

A Statistical Analysis of the Modulus of Elasticity and Compressive Strength of Concrete C45/55 for Pre-stressed Precast Beams

Random behavior of concrete C45/55 XF2 used for prefabricated pre-stressed bridge beams is described on the basis of evaluating a vast set of measurements. A detailed statistical analysis is carried out on 133 test results of cylinders 150 ~ 300 mm in size. The tests have been running in laboratories of the Klokner Institute. A single worker took all specimens throughout the period, and the subsequent measurements of the static modulus of elasticity and the compressive strength of the concrete were performed. The measurements were made at the age of 28 days after specimens casting, and only one testing machine with the same capping method was used. Suitable theoretical models of division are determined on the basis of tests in good congruence, with the use of Z2 and the Bernstein criterion. A set of concrete compressive strength （carried out on 133 test results of cylinders 150 ~ 300 mm after test of static modulus of elasticity） shows relatively high skewness in this specific case. This cause that limited beta distribution is better than generally recommended theoretical distribution for strength the normal or lognormal. The modulus of elasticity is not significantly affected due to skewness because the design value is based on mean value.

Predictive analysis of stress regime and possible squeezing deformation for super-long water conveyance tunnels in Pakistan

The prediction of the stress field of deep-buried tunnels is a fundamental problem for scientists and engineers. In this study, the authors put forward a systematic solution for this problem. Databases from the World Stress Map and the Crustal Stress of China, and previous research findings can offer prediction of stress orientations in an engineering area. At the same time, the Andersonian theory can be used to analyze the possible stress orientation of a region. With limited in-situ stress measurements, the Hock-Brown Criterion can be used to estimate the strength of rock mass in an area of interest by utilizing the geotechnical investigation data, and the modified Sheorey＇s model can subsequently be employed to predict the areas＇ stress profile, without stress data, by taking the existing in-situ stress measurements as input parameters. In this paper, a case study was used to demonstrate the application of this systematic solution. The planned Kohala hydropower plant is located on the western edge of Qinghai-Tibet Plateau. Three hydro-fracturing stress measurement campaigns indicated that the stress state of the area is SH - Sh 〉 Sv or SH 〉Sv 〉 Sh. The measured orientation of Sn is NEE （N70.3°-89°E）, and the regional orientation of SH from WSM is NE, which implies that the stress orientation of shallow crust may be affected by landforms. The modified Sheorey model was utilized to predict the stress profile along the water sewage tunnel for the plant. Prediction results show that the maximum and minimum horizontal principal stres- ses of the points with the greatest burial depth were up to 56.70 and 40.14 MPa, respectively, and the stresses of areas with a burial depth of greater than 500 m were higher. Based on the predicted stress data, large deformations of the rock mass surrounding water conveyance tunnels were analyzed. Results showed that the large deformations will occur when the burial depth exceeds 300 m. When the burial depth is beyond 800 m, serious squeezing deformations will occur in the surrounding rock masses, thus requiring more attention in the design and construction. Based on the application efficiency in this case study, this prediction method proposed in this paper functions accurately.

Vibrational characteristics of piping system in air conditioning outdoor unit

The modal analysis of piping system in air conditioner (AC) outdoor unit is essential to investigate the vibration properties of the system. In view of the growing significance of numerical finite element (FE) model for vibration behaviour prediction, the AC piping elastic end support characterization has been explored. The axial and radial stiffness variables (ka, kr1, kr2) of the compressor-piping mounting are obtained and represented by dynamic stiffness of compressor grommet. They are obtained from dynamic load deflection test based on compressor operating condition such as excitation frequency and amplitude. The unknown stiffness variables of the other tube end (chassis-piping mounting) are determined by parameter fine tuning. An experimental modal analysis using impact hammer test has also been employed to determine the vibration properties such as natural frequencies, mode shapes and damping ratio of the piping structures. The modal parameters acquisition using SCADAS mobile acquisition system and LMS Impact Testing software is compared with the corresponding simulated modal properties using Abaqus. Most of the simulated natural frequencies achieve good correlation with the measured frequencies and it is reasonably a good prediction model to predict vibration behaviour of AC piping structures.

Unseen head pose prediction using dense multivariate label distribution

Accurate head poses are useful for many face-related tasks such as face recognition, gaze estimation,and emotion analysis. Most existing methods estimate head poses that are included in the training data(i.e.,previously seen head poses). To predict head poses that are not seen in the training data, some regression-based methods have been proposed. However, they focus on estimating continuous head pose angles, and thus do not systematically evaluate the performance on predicting unseen head poses. In this paper, we use a dense multivariate label distribution(MLD) to represent the pose angle of a face image. By incorporating both seen and unseen pose angles into MLD, the head pose predictor can estimate unseen head poses with an accuracy comparable to that of estimating seen head poses. On the Pointing'04 database, the mean absolute errors of results for yaw and pitch are 4.01?and 2.13?, respectively. In addition, experiments on the CAS-PEAL and CMU Multi-PIE databases show that the proposed dense MLD-based head pose estimation method can obtain the state-of-the-art performance when compared to some existing methods.