基于神经网络模型的水质监测与评价系统

对水环境的监测与评价，可以掌握水质现状及其发展趋势，为水资源的开发利用和管理提供科学依据。水质评价是建立在水质监测基础之上的。首先结合我国水环境监测技术规范与标准，合理地选择监测项目与监测仪器，建立水质监测系统。然后在水质监测所获数据基础上，运用人工神经网络的理论和方法，通过BP网络不断的学习与训练，归纳出评价标准与评价结果间复杂的非线性关系，建立水质评价的BP神经网络模型系统。经实际应用表明，该系统具有很强的学习、联想和容错功能。为水质监测与评价提供了一条新的途径。     

Adverse perinatal outcome in patients screen-positive for neural tube defects and fetal down syndrome

An association between various abnormal mid-trimester maternal serum analyte values and adverse perinatal outcome has been reported. From an original sample of 14 857 women, we observed five women who were ‘screen-positive’ for both neural tube defects [maternal serum alpha-fetoprotein (MSAFP) ≥2·5 multiples of the median] and Down syndrome [risk ≥1/274 using MSAFP, maternal serum unconjugated oestriol (MSuE3), maternal serum human chorionic gonadotropin (MShCG), and maternal age]. The four patients who elected to undergo amniocentesis all demonstrated both normal karyotype and normal amniotic fluid AFP levels. All five cases were associated with intrauterine growth retardation (IUGR) and abnormal pregnancy outcomes. Two cases exhibiting severe IUGR on ultrasound examination were terminated at 19·1 and 21·2 weeks, respectively; the former also exhibited fetal calcifications and positive maternal serology for toxoplasmosis. In another case, fetal demise occurred at 36 weeks' gestation in a patient who had been treated for syphilis in the second trimester. Neither infection was confirmed in fetal tissue studies. Though resulting in live births, the remaining two cases required operative deliveries; emergency Caesarean sections for fetal distress were performed at 38 and 32 weeks, respectively, the latter case being associated with severe pre-eclampsia. We conclude that elevated mid-trimester MSAFP levels concurrent with maternal serum analyte values associated with increased risk for fetal Down syndrome may presage a poor perinatal outcome, particularly IUGR and possibly congenital infection.     

珠江口海岸线变化的遥感监测

珠江口、香港及澳门地区海岸线的变化近十几年来十分迅速 ,采用常规方法及时、定量地测量这种变化十分困难。本研究应用多时相Landsat卫星遥感图像 ,采用神经网络分类方法 ,监测海岸线的变化并计算增长的陆地面积。结果表明 ,人为的围海造田 ,香港、澳门机场及相关高速公路、港口等设施的建设是海岸线变化的最主要原因。     

基于神经网络的土霉素废水处理试验仿真系统

土霉素结晶母液属于高浓度的有机废水，用传统的处理方法不能明确其反应机理，试验结果也并不理想。在已有的实验数据基础上，利用神经网络建立水处理试验仿真系统，通过计算机模拟预测出各种试剂的合理用量，最后在实验室进行验证，取得了良好的效果。     

活性污泥系统神经网络建模与仿真研究

采用神经网络技术对松江污水厂污水处理活性污泥系统进行建模试验研究，在对实际运行数据按机理准则和范围准则剔除异常数据后，将样本数据随机分成训练样本、检验样本和测试样本。用试凑法确定合理的神经网络隐层节点数，以避免采用过大或过小的网络结构，在训练过程中用检验样本实时监控从而避免“过训练”现象的影响，较好地解决神经网络方法建模的两大难题，从而建立可靠、有效的活性污泥系统神经网络模型。并应用建立的网络模型对活性污泥系统的运行情况进行了仿真研究。建模研究表明，神经网络技术能较好地应用于活性污泥系统的建模，模型具有较好的泛化能力，有很好的实用价值。     

Probabilistic analysis of aluminium production explosion accidents based on a fuzzy Bayesian network

Explosion accidents of molten aluminium in contact with water during aluminium production often occur and may cause injury and death. In this paper, a fuzzy Bayesian network (BN) was employed to probabilistically analyse the explosion accident of molten aluminium in contact with water. A fault tree-Bayesian network (FT-BN) model was established in the cause-effect analysis of the explosion accident, including three processes: electrolysis, molten aluminium transportation and aluminium casting. Fifty-three nodes were proposed in the model to represent the evolution process of the explosion accident from failure causes to consequences. Furthermore, the occurrence probabilities of basic events (BEs) were determined by expert judgement with weighted treatments based on fuzzy theory. By giving certain occurrence probabilities of each BE, the probability of an explosion accident was estimated. Subsequently, importance measures were assessed for each BE, which could reflect the impact on the occurrence of the top event (TE), and the final ranks were provided. The results indicate that using wet ladles and tools, water on the ground, breakage of the tap hole, damage to the casting mould, and leakage of circulating water are five main problems that cause explosion accidents. Safety advice was provided based on the analysis results. This study can help decision makers improve the safety management of aluminium production.     

储气库注采管柱螺纹失效动态风险评估*

为解决储气库注采管柱螺纹失效问题,识别注采管柱螺纹失效致因与后果,基于蝴蝶结和贝叶斯网络方法构建注采管柱螺纹动态失效风险分析模型,采用模糊集理论计算模型变量先验概率,并评估注采管柱失效后果概率,从而推断注采管柱螺纹失效关键致因因素;引入先兆数据,评估注采管柱螺纹动态失效风险态势。结果表明:气体中携带固体颗粒、上螺纹速度过快、注采温度高、地层断裂等13个因素对螺纹失效风险影响较大;螺纹失效概率逐渐增大,螺纹失效后果也越来越严重,需要监控螺纹失效关键致因以降低螺纹失效的风险。     

基于疲劳模式识别的VDT作业工间休息机制*

为保障作业人员身心健康和作业效率,运用E-Prime软件模拟认知性VDT持续作业,通过方差分析提出作业疲劳综合评价指标体系,并使用客观绩效指标和生理指标作为输入变量,主观疲劳综合指数作为输出变量,训练BP神经网络,对作业疲劳进行模式识别;提出认知性VDT持续作业工间休息机制。结果表明:通过正确反应时间、注视时间、瞳孔直径、眨眼频率4项指标,对VDT持续作业疲劳进行模式识别的结果可信度较高。因此,基于上述4项指标提出的工间休息机制客观有效。     

夹点技术在冶金企业节水减排中的应用研究

水夹点技术可以有效地节约工业新鲜水用量,同时减少废水排放量。尽管水夹点技术在理论上已经比较成熟,国内外在石化、化工等行业应用的报道较多,但在冶金行业鲜有报道。介绍了水夹点技术的原理,提出了将其应用于冶金行业工程实践的实施步骤,并以首钢某公司节水改造为例,给出了用水网络优化方案。实施结果表明节水效果良好。     

基于MAS的制导雷达网络化抗干扰作战体系结构研究

通过对地空导弹网络化抗干扰作战的分析,结合DAI(Distributed Artificial Intelligence,分布式人工智能)技术中的MAS(Multi-Agent System,多智能体系统)技术,建立了基于MAS的制导雷达网络化抗干扰作战系统,并给出了该系统的Agent组成框架,定义并说明了各Agent的功能及相互关系.