Effect of strain waveform on creep-fatigue life for Sn–8Zn–3Bi solder

This paper describes the creep‐fatigue life of Sn–8Zn–3Bi under push–pull loading. Creep‐fatigue tests were carried out using Sn–8Zn–3Bi specimens in fast–fast, fast–slow, slow–fast, slow–slow and hold–time strain waveforms. Creep‐fatigue lives in the slow–slow and hold‐time waveforms showed a small reduction from the fast–fast lives but those in the slow–fast and fast–slow waveforms showed a significant reduction from the fast–fast lives. Conventional creep‐fatigue life prediction methods were applied to the experimental data and the applicability of the methods was discussed. Creep‐fatigue characteristics of Sn–8Zn–3Bi were compared with those of Sn–3.5Ag and Sn–37Pb.     

An approach to efficient business intelligent system for financial prediction

A concept of business intelligent system for financial prediction is considered in this paper. It provides data needed for fast, precise and good business decision support to all levels of management. The aim of the project is the development of a new online analytical processing oriented on case-based reasoning (CBR) where a previous experience for every new problem is taken into account. Methodological aspects have been tested in practice as a part of the management information system development project of “Novi Sad Fair”. A case study of an improved application of CBR in prediction of future payments is discussed in the paper. This paper is originally presented at The International Conference on Hybrid Information Technology 2006, at the special session on “Intelligent Information Systems for Financial Engineering”, November 2006 in Cheju Island, Korea.     

A neural network model for fault detection in conjunction with a programmable logic controller

This paper discusses the feasibility of using neural networks as a tool in the fault detection process. A neural network is integrated with a state language programmable logic controller, an important device in an automatic control system. Time series data related to time spent in a state is gathered and used as input into a neural network, for the purpose of identifying when a fault has occurred. A feedforward neural network is used to identify which (if any) of three types of faults may have occurred. Experimental results related to sensitivity and accuracy measures are presented. A brief review of related applications and research is also presented.     

一种评价机器磨损和润滑油质量的新方法

提出用表征大型机械系统健康状态的相对劣化度作为监控机械磨损状态和油品质量变化的综合判断指标，以便结合反映机器工作状态的其它因素，共同评定机器的健康状态。以柴油机为例，对监测得到的柴油机润滑油的铁谱参数、磨损金属元素含量和油品理化性能等数据进行综合分析和处理，所得相对劣化度的变化趋势，较准确地反映了柴油机的工作状况。该方法不仅简单实用，而且便于将油液监测技术与其他监测技术（如振动诊断技术）结合起来，用一统一指标描述机器的健康状况，达到监测和预报的目的，为开发基于多种监测技术的智能诊断系统打下基础。     

快速二阶BP网络及其在城市用水量预测中的应用

针对BP网络收敛速度慢，易导致局部极小值的缺点，提出一种快速二阶BP网络，并以城市年用水量预测为例，与BP网络对比，结果表明，该方法加快了收敛速度，提出了结果的准确度。     

火烧油层技术在庙5块低渗透稠油油藏中的应用

方法在物理模拟的基础上，利用数值模拟及油藏工程方法，对影响火烧油层的技术参数进行了优选研究，并对影响火驱成败的油藏地质参数、注气参数进行了分析。目的寻找适合庙５块低渗透稠油油藏的开采方法。结果提出了庙５块火驱的最佳开采方式、点火参数及注气参数；庙５块火驱生产后，平均单井日产液由０１ｔ上升到５６ｔ，平均单井日产油由０１ｔ上升到３５ｔ，生产２６ｄ后由于压风机供风不足被迫停止火驱注气；从数模结果看：火驱最终采收率可达３９８％。结论火烧油层是一种潜力很大的稠油开采方法，但其物理、化学反应机理复杂，火烧前缘难以控制；庙５块火驱初期虽然见到了一定的生产效果，但没有取得经济效益     

地震资料精细处理和解释在徐家围子油田的应用

以地震资料精细处理和解释在大庆长垣外围徐家围子油田开发中的成功应用为例，论述了地震地质综合描述技术在地质情况复杂的低、特低渗透油田开发中的应用效果。     

Vibration Monitoring and Diagnosis of Pipe-line Pumps on Offshore Platforms

ＶｉｂｒａｔｉｏｎＭｏｎｉｔｏｒｉｎｇａｎｄＤｉａｇｎｏｓｉｓｏｆＰｉｐｅｌｉｎｅＰｕｍｐｓｏｎＯｆｓｈｏｒｅＰｌａｔｆｏｒｍｓＺｈｅｎｇＷｅｎＴｅｃｈｎｏｌｏｇｉｃａｌＦａｃｕｌｔｙｏｆＭａｉｎｔｅｎａｎｃｅＥｎｇｉｎｅｒｉｎｇＧｕａｎｇｚｈｏｕ...     

地震数据油气预测中的属性优化方法

本文简单介绍了智能信息处理中新出现的RoughSet（RS）理论及属性选择方法，从双相介质地震波传播理论角度，探讨了地震数据油气预测属性优化原理，提出了基于RS理论的地震数据油气预测属性优化方法。实际应用表明；本方法速度快、易实现，而且在优选属性、最大程度地减少提取地震属性种数、提高分类正确率等方面，明显优于其它方法。本方法将成为地震数据油气预测的一种有效手段。     

Measurement and prediction of pressure drop in two-phase flow

Experimental data for air–water two-phase co-current flow in two different pipe diameters were used to test the prediction of pressure drop by a number of existing theories and correlations. Several models are shown to be useful for prediction, particularly with the stratified regimes which have proved difficult to handle in the past. The model suggested by Olujic proved to be of particular value.