马尔可夫链在产品可靠性预测中的应用

事物未来的状态仅仅受事物现状的影响，而与过去的状态无关，也就是具有马尔可夫性。用马尔可夫链的理论与方法，对具有马尔可夫性产品的可靠性进行预测，既为产品的可靠性设计和产品售后服务的经济性分析提供了参考，也为马尔可夫模型的实际应用拓广了范围。通过实例说明在数学软件的帮助下这种预测方法的简单可行性。     

对我国石油可采资源量的预测研究

回顾了世界上现行的可采资源量预测方法,总结分析了在我国石油勘探开发过程中大型油气田的发现规律及储采比变化规律,探讨了累积发现可采储量、累积产量与可采资源量三者之间的内在关系及储采比的变化对它们的影响.在此基础上,利用累积发现的可采储量与累积产量建立了预测可采资源量的有效方法———全程历史拟合法和储采比递减阶段曲线拟合法.利用上述两种方法预测出中国石油的经济可采资源量为107.8×10⁸t,次经济的可采储量约为(27～36)×10⁸t,还对部分油区的可采资源量进行了预测.预测结果表明,两种方法对比使用,能获得较好的预测效果.     

改进BP网络在航材需求预测中的应用

针对航材备件需求预测问题,在对影响航材备件需求量的多个因素进行分析研究的基础上,运用改进BP神经网络算法进行预测的仿真实验。实验结果表明,改进BP神经网络能够对积累的历史数据进行充分的应用,并且有较高的预测准确性。     

Stock Price Forecasting: An Echo State Network Approach

Forecasting stock prices using deep learning models suffers from problems such as low accuracy, slow convergence, and complex network structures. This study developed an echo state network (ESN) model to mitigate such problems. We compared our ESN with a long short-term memory (LSTM) network by forecasting the stock data of Kweichow Moutai, a leading enterprise in China’s liquor industry. By analyzing data for 120, 240, and 300 days, we generated forecast data for the next 40, 80, and 100 days, respectively, using both ESN and LSTM. In terms of accuracy, ESN had the unique advantage of capturing nonlinear data. Mean absolute error (MAE) was used to present the accuracy results. The MAEs of the data forecast by ESN were 0.024, 0.024, and 0.025, which were, respectively, 0.065, 0.007, and 0.009 less than those of LSTM. In terms of convergence, ESN has a reservoir state-space structure, which makes it perform faster than other models. Root-mean-square error (RMSE) was used to present the convergence time. In our experiment, the RMSEs of ESN were 0.22, 0.27, and 0.26, which were, respectively, 0.08, 0.01, and 0.12 less than those of LSTM. In terms of network structure, ESN consists only of input, reservoir, and output spaces, making it a much simpler model than the others. The proposed ESN was found to be an effective model that, compared to others, converges faster, forecasts more accurately, and builds time-series analyses more easily.     

An enhanced,acoustic emission-based,single-fiber-composite test

In the single-fiber-composite (SFC) test, a fiber imbedded in a matrix is loaded in tension, resulting in a fragmentation of the fiber. In the conventional version of this test, the final fiber fragmentation length distribution is used with a micro-mechanical model to determine the average fiber/matrix interfacial shear stress. In the enhanced version of this test, one also determines the applied stress at each fiber fracture, and from this, one can evaluate the strength of the fiber at short gage lengths. In our measurement system, we utilize an acoustic emission (AE) technique to detect the fiber fractures and to locate the fiber breaks and so determine both the fiber failure stresses as well as the fiber fragmentation lengths while the test is in progress. Critical to the success of this test is a broadband AE system that utilizes point-like AE sensors, procedures for evaluatingin situ, the wavespeed of the first wave arrival and signal processing techniques for determining the arrival time of this signal as precisely as possible for a broad range of wave shapes. Here we describe the application of such an enhanced SFC test procedure to investigate the failure of a Nicalon fiber in an epoxy matrix.     

The Structure of the Irreversibly Bound Adhesion Promoter-Substrate Interfacial Layer of γ-Aminopropylsilanetriol on Crystalline Si, as Measured by XPS and FTIR

The irreversibly bound interfacial layer deposited by the γ-aminopropysilanetriol adhesion promoter onto a crystalline silicon substrate, which remains even after profuse washing, was found by XPS to have resulted from the fragmentation and rearrangement of the original γ-aminopropylsilanetriol molecule. A mechanism is proposed, involving the homolytic scission of the terminal N-C bond. One of the subsequent reactions is believed to involve hydrogen loss by abstraction and the formation of a terminal vinyl group, which bonds to the substrate. Support for this mechanism is found in IR spectroscopy of this layer.     

基于KPCA-PSO-SVM的径流预测研究

为提高径流预测模型的准确性与稳定性,对KPCA-PSO-SVM的径流预测方法进行了研究。在分析径流影响因素的基础上,利用核主成分分析(KPCA)法对径流影响因子进行非线性特征提取,获得主成分作为支持向量机(SVM)的输入变量,建立了径流预测SVM模型,其中模型参数通过粒子群算法(PSO)进行优化。模型建立后,以新疆伊犁河雅马渡站中长期径流预测为例进行分析。预测分析结果表明,在拟合和检验阶段模型的平均相对误差分别为0.77%和7.64%,与其他预测模型比较,基于KPCA-PSO-SVM方法建立的径流预测模型有较好的预测和泛化能力,是一种行之有效的中长期径流预测方法。     

C#利用Web Service编程接口实现动态天气预报

许多政府或企业网站除展示与本单位密切相关的信息外,往往也集成一些小的功能性的、与用户日常生活密切相关的,类似于提供火车时刻表、天气预报等辅助信息,采用C#利用Web Service提供的编程接口实现了实时天气预报功能,并能根据访问者所在地自动提供其相关的天气信息。     

基于改进的BASS模型的服装产品生命周期研究

为提高服装的销售预测准确度,通过产品的生命周期曲线模型,使得服装销售预测的定性分析与定量预测有机地结合在一起。针对目前服装产品生命周期曲线模型的局限性,引入改进的BASS模型,对服装产品生命周期进行研究。通过销售实例探讨改进的BASS模型用于描述服装生命周期的可行性,建立了以改进的BASS模型为基础的服装产品生命周期模型,并利用该模型对服装销售量做预测,取得了比其他模型更高的精度。