煤矿主提胶带运输系统远程自动化集中控制的工程实践

从煤矿生产作业环境的安全性出发,结合机械化、自动化技术的发展趋势,提出煤矿主提胶带运输系统远程自动化集中控制的技术方案,并以成功实例验证了方案的可操作性,节能效果显著。     

合流制排水系统降雨径流污染物的特性及来源

在昆明市典型合流制排水小区对降雨径流进出水水量、水质进行了研究,旨在揭示城市区域合流制排水系统中降雨径漉不同来源的污染物特性及各个污染源的比倒.分别监测了合流制排水系统日常污水以及4场降雨期间小区出口断面、街道、屋顶、庭院降雨径流的水量、水质.结果表明,人为干扰是影响城市径流污染物输出强度的主要因素,城市下垫面降雨径流污染物输出浓度顺序为:道路>庭院>屋顶,道路是城市面源污染的关键源区;道路次降雨径流量约25%,却产出了40%～80%的污染物,而屋顶次降雨径流量约50%,却仅有4%～30%的污染物负荷.合流制排水系统中管道沉积物在降雨期间的迁移是重要的污染源,4场降雨中管道沉积物的TN、TP、SS、COD和BOD5的污染贡献率在30%以上.降雨强度是影响管道沉积物输出的重要因素,在高强度降雨下,管道沉积物污染贡献率高50%以上.在不同的降雨特性条件下,合流制排水系统主导污染源有所不同.     

污水处理中的计算机监控及无线数据传输

在分析大型污水处理厂计算机监控系统运行的基础上 ,从理论上分析了计算机监控、无线数据传输、无线网络的技术原理及抗干扰性、保密性。介绍部分工控产品及无线网络产品 ,以及在环保水处理及相关部门中的应用。     

环氧化合物分子结构与致变活性的关系

由化学物质毒性效应登录(RTECS)1998年光盘系统检索获得86种环氧化合物对鼠沙门氏菌致变活性数据.应用主成分分析法从11种分子描述符中选择出5种对致变活性有明显影响的描述符:碳原子数,苯环数,氢原子数,烷基数和氧原子数.通过样本学习集训练并优化神经网络结构,建模分类预报:对于86个样本,低和高2类活性,正确分类率达到92%.结果表明:3～4个骈接苯环的环氧化物的特殊结构具有很强的致变活性.     

硫酸盐还原过程中SRB的限制性生态因子的BP神经网络建模与仿真

利用BP神经网络对产酸脱硫反应器（专利设备，ZL：98240801.3）处理高浓度硫酸盐废水时硫酸盐还原菌（SRB）的限制性生态因子（COD/SO^2-4比、pH值、ALK、SO^2-4负荷率）进行建模与仿真，从而实现了多变量函数关系的映射与泛化，并从数学生态学角度定量表征了产酸脱硫微生物生态系统中SRB种群的代谢活性与实现生态位。     

Prenatal diagnosis in three cases of iniencephaly with unusual postmortem findings

Iniencephaly is a rare and lethal congenital malformation of the neural tube characterized by occipital bone defect, cervical dysraphism, fixed retroflexion of the fetal head and severe lordosis of the cervicothoracic spine. The etiology is unknown. Prenatally diagnosed cases of iniencephaly are rare because careful and early ultrasonographic evaluation is necessary. We present three cases of iniencephaly prenatally diagnosed by sonography at 20–22 weeks' gestation in which therapeutic abortion was induced. The sonographic findings were compatible with the postmortem findings. The present cases of iniencephaly were found to carry unusual associated malformations such as two lobes in the right lung and chorangiosis of the placenta. Only hypoplastic lungs have been reported by previous authors. We also studied the 677C→T mutation on the methylenetetrahydrofolate reductase gene in the parents in one of the present cases. The mother was found to be heterozygous for the 677CT polymorphism. Copyright © 2001 John Wiley & Sons, Ltd.     

人工神经元网络对水处理系统建模适应性的研究

针对水处理系统的特点和研究中的难点，引入人工神经元网络的理论和思想，提出了水处理系统的神经网络分析方法．通过建立基于ＢＰ人工神经元网络的臭氧生物活性炭系统的模型，具体地考察了人工神经元网络对水处理系统建模的适应性，使水处理系统的研究迈向智能化和控制化．     

Rural landscape planning case study of Nanhua State Farm

１ＩｎｔｒｏｄｕｃｔｉｏｎＨｉｇｈｌｙｐｒｏｄｕｃｔｉｖｅｌａｎｄｕｓｅｒｅｓｕｌｔｓｉｎａｃｏｎｔｉｎｕｏｕｓｃｈａｎｇｅｏｆｌａｎｄｓｃａｐｅｓｉｎｒｕｒａｌａｒｅａｓ．Ｕｎｄｅｒｔｈｅｉｍｐａｃｔｏｆｃｒｏｐｐｒｏｄｕｃｔｍａｒｋｅｔｓ，ｌａｎ...     

Modelling and Prediction of Diesel Engine Performance using Relevance Vector Machine

Diesel engines are being increasingly adopted by many car manufacturers today, yet no exact mathematical diesel engine model exists due to its highly nonlinear nature. In the current literature, black-box identification has been widely used for diesel engine modelling and many artificial neural network (ANN) based models have been developed. However, ANN has many drawbacks such as multiple local minima, user burden on selection of optimal network structure, large training data size, and over-fitting risk. To overcome these drawbacks, this article proposes to apply an emerging machine learning technique, relevance vector machine (RVM), to model and predict the diesel engine performance. The property of global optimal solution of RVM allows the model to be trained using only a few experimental data sets. In this study, the inputs of the model are engine speed, load, and cooling water temperature, while the output parameters are the brake-specific fuel consumption and the amount of exhaust emissions like nitrogen oxides and carbon dioxide. Experimental results show that the model accuracy is satisfactory even the training data is scarce. Moreover, the model accuracy is compared with that using typical ANN. Evaluation results also show that RVM is superior to typical ANN approach.     

基于人工神经网络建模的PTC功率智能检测技术

PTC是家用空调器中主要器件之一,具有耗电量大、非线性的特征。目前PTC常用的功率检测方法是通过"专用电量计量芯片结合电压、电流采样电路"来实现,存在成本高和可靠性低问题。提出一种基于人工神经网络的PTC功率纯软件计算方法,无需增加任何硬件成本。通过实验验证,精度达±3%,满足产品化需求,成熟可靠。