Wind speed forecasting based on the hybrid ensemble empirical mode decomposition and GA-BP neural network method

Wind speed is the major factor that affects the wind generation, and in turn the forecasting accuracy of wind speed is the key to wind power prediction. In this paper, a wind speed forecasting method based on improved empirical mode decomposition (EMD) and GA-BP neural network is proposed. EMD has been applied extensively for analyzing nonlinear stochastic signals. Ensemble empirical mode decomposition (EEMD) is an improved method of EMD, which can effectively handle the mode-mixing problem and decompose the original data into more stationary signals with different frequencies. Each signal is taken as an input data to the GA-BP neural network model. The final forecasted wind speed data is obtained by aggregating the predicted data of individual signals. Cases study of a wind farm in Inner Mongolia, China, shows that the proposed hybrid method is much more accurate than the traditional GA-BP forecasting approach and GA-BP with EMD and wavelet neural network method. By the sensitivity analysis of parameters, it can be seen that appropriate settings on parameters can improve the forecasting result. The simulation with MATLAB shows that the proposed method can improve the forecasting accuracy and computational efficiency, which make it suitable for on-line ultra-short term (10 min) and short term (1 h) wind speed forecasting.     

A novel model: Dynamic choice artificial neural network (DCANN) for an electricity price forecasting system

Big data mining, analysis, and forecasting always play a vital role in modern economic and industrial fields. Thus, how to select an optimization model to improve the forecasting accuracy of electricity price is not only an extremely challenging problem but also a concerned problem for different participants in an electricity market due to our society becoming heavily reliant on electricity. Many researchers developed hybrid models through the use of optimization methods, classical statistical models, artificial intelligence approaches and de-noising methods. However, few researchers aim to select reasonable samples and determine appropriate features when forecasting electricity price. Based on the Index of Bad Samples Matrix (IBSM), a novel method to dynamically confirm bad training samples, and the Optimization Algorithm (OA), DCANN and Updated DCANN are proposed in this paper for forecasting the day-ahead electricity price. This model is a hybrid system of supervised and unsupervised learning and creatively applies the idea of deleting bad samples and searching quality inputs to develop and learn, which is unlike BPANN, RBFN, SVM and LSSVM. Numerical results show that the proposed model is not only able to approximate the actual electricity price (normal or high volatility) but also an effective tool for h-step-ahead forecasting (h is less than 10) compared to benchmarks.     

履带板受力情况分析

履带板作为履带式车辆的主要承载零件,由于其工况的复杂性,使它的受力情况很难得到计算.在前人的基础上,对履带车辆的转弯和履带板的啮合工况进行分析,得到了这两种工况下履带板的受力情况.对履带板受力情况的研究有利于更好的设计履带板.     

基于刚柔耦合模型的强夯机动力学分析

履带式强夯机工作级别高,工作环境恶劣,在突然释放夯锤时,整机受到强大冲击.在ADAMS动力学仿真环境下联合Pro/E和ANSYS软件建立400 t·m强夯机整机的刚柔耦合模型,对其突然卸载工况进行仿真分析,研究卸载过程中结构件的振动响应、整机的稳定性,对柔性体的动态应力及整机动态响应参数进行分析,为整机的疲劳寿命分析及部件的设计改进与优化提供载荷谱数据.     

有限元法计算大吨位伸缩臂起重机起重性能

起重性能是起重机综合起重能力的体现,准确并快速地计算起重性能对起重机的设计至关重要.将大吨位伸缩臂起重机臂架系统简化为梁,建立了简化模型,分析外载荷,采用几何非线性有限元理论计算某一工况下单元的变形和节点力,由复合应力与许用应力的关系求出额定起重量.通过算例将非线性有限元理论计算出的结果、线性理论计算的结果、样机试验实测出的结果做对比,验证了简化的合理性和此种方法在起重机起重性能计算上应用的可靠性.     

Full-duplex fiber-wireless link with 40 Gbit/s 16-QAM signals for alternative wired and wireless accesses based on homodyne/heterodyne coherent detection

A novel full-duplex fiber-wireless link with 40 Gbit/s 16-ary quadrature amplitude modulation (QAM) signals is proposed to provide alternative wired and wireless accesses for the user terminals. In the central station (CS), the downstream signal for wired and wireless accesses is beared onto the CW laser source via an optical I/Q modulator to realize the QAM modulation. At the hybrid optical network unit (HONU), a tunable laser is used to provide coherent optical local oscillator for homo-/heterodyne beating to coherently down-convert the baseband optical signal to the baseband electrical one for wired access or to the mm-wave one for wireless access according to the requirement of the user terminals. Simultaneously, the lightwave from the tunable laser is also used as the uplink optical carrier for either wired or wireless access, and is modulated colorlessly by the baseband or mm-wave signal of the uplink alternatively. After filtering, only one tone carrying the uplink signal is transmitted back to the CS even for the wireless access. The theoretical analysis and simulation results show that our proposed full-duplex link for the alternative wired and wireless accesses maintains good performance even when the transmission link with standard single mode fiber (SSMF) is extended to 30 km.     

Road transport-related energy consumption: Analysis of driving factors in Tunisia

The rapid growth of urban population and the development of road infrastructures in Tunisian cities have brought about many environmental and economic problems, including the rise scored in energy consumption and the increase in the quantity of gas emissions arising from road transport. Despite the critical nature of such problems, no policies have yet been adopted to improve energy efficiency in the transport sector. This paper aims to determine driving factors of energy consumption change for the road mode. It uses decomposition analysis to discuss the effects of economic, demographic and urban factors on the evolution of transport energy consumption. The main result highlighted in the present work is that vehicle fuel intensity, vehicle intensity, GDP per capita, urbanized kilometers and national road network are found to be the main drivers of energy consumption change in the road transport sector during 1990–2006 period. Consequently, several strategies can be elaborated to reduce road transport energy. Economic, fiscal and regulatory instruments can be applied in order to make road transport more sustainable.     

A neuro-fuzzy-multivariate algorithm for accurate gas consumption estimation in South America with noisy inputs

This paper presents an adaptive-network-based fuzzy inference system (ANFIS)-fuzzy data envelopment analysis (FDEA) algorithm for improvement of long-term natural gas (NG) consumption forecasting and analysis. Two types of ANFIS (Types 1 and 2) have been proposed to forecast annual NG demand. For each type, several ANFIS models have been constructed and tested in order to find the best ANFIS for NG consumption. Two parameters have been considered in construction and examination of plausible ANFIS models (Type 1). Six different membership functions and several linguistic variables are considered in building ANFIS. Also different value of cluster radius has been used to construct ANFIS (Type 2) models. The proposed models consist of two input variables, namely, Gross Domestic Product (GDP) and Population. All trained ANFIS are then compared with respect to mean absolute percentage error (MAPE), Root mean square normalized error (RMSE) and correlation coefficient (R) using data envelopment analysis (DEA). To meet the best performance of the intelligent based approaches, data are pre-processed (scaled) and finally our outputs are post-processed (returned to its original scale). FDEA is used to examine the behavior of gas consumption. To show the applicability and superiority of the ANFIS–FDEA algorithm, actual NG consumption in six Southern America countries from 1980 to 2007 is considered. NG consumption is then forecasted up to 2015. The ANFIS–FDEA algorithm is capable of dealing both complexity and uncertainty as well several other unique features discussed in this paper.     

The load-balanced multi-dimensional bin-packing problem

The bin-packing problem is one of the most investigated and applicable combinatorial optimization problems. In this paper we consider its multi-dimensional version with the practical extension of load balancing, i.e. to find the packing requiring the minimum number of bins while ensuring that the average center of mass of the loaded bins falls as close as possible to an ideal point, for instance, the center of the bin. We formally describe the problem using mixed-integer linear programming models, from the simple case where we want to optimally balance a set of items already assigned to a single bin, to the general balanced bin-packing problem. Given the difficulty for standard solvers to deal even with small size instances, a multi-level local search heuristic is presented. The algorithm takes advantage of the Fekete–Schepers representation of feasible packings in terms of particular classes of interval graphs, and iteratively improves the load balancing of a bin-packing solution using different search levels. The first level explores the space of transitive orientations of the complement graphs associated with the packing, the second modifies the structure itself of the interval graphs, the third exchanges items between bins repacking proper n-tuples of weakly balanced bins. Computational experiments show very promising results on a set of 3D bin-packing instances from the literature.     

资源枯竭型国有企业关闭破产研究

关闭破产是资源枯竭型国有企业主要退出途径之一，涉及大量的资产、债务和职工，很客易由经济问题演变为社会问题。资源枯竭型国有企业的关闭破产属于政策性关闭破产，《破产法》等正式法律并不完全适用解决此类企业的关闭破产问题。在实施过程中，逐渐形成了“省市结合，以市为主”、“社会职能属地化管理”等经验，但同时也存在着职工安置困难、清算资金匮乏、地方政府压力过大等问题。为此，应该采取依托地方政府，加强再就业工作；完善社会保障体系；强化资产变现工作等措施。此外，从长远来看，资源型国有企业应该循序渐退、推行产权制度改革、加快资源枯竭型城市（镇）经济转型步伐等，以从根本上解决资源枯竭型国有企业退出问题。