ABC算法优化SVR的磨损故障预测模型

目的为了提高故障预测的精度,针对支持向量回归SVR(Support vector machine for regression,SVR)参数选择困难的问题,提出一种采用人工蜂群(artificial bee colony,ABC)算法优化支持向量回归(SVR)的故障预测模型(ABC-SVR)。方法该模型先对样本数据进行重构,然后将故障预测误差(适应度)作为优化目标,通过ABC算法寻优找到最优的SVR参数,建立故障预测模型。最后通过实例仿真验证模型的优越性。结果采用ABC算法优化的SVR故障预测模型进行时间序列预测,能够较好地跟踪发动机滑油金属元素浓度的变化过程,并且能够提前2个取样时间预测异常情况的出现。结论 ABC-SVR模型有效解决了SVR参数选择难题,能够更加准确地表现故障变化规律,提高了故障预测精度。     

生态高负荷土地快速渗滤系统处理猪场废水的效能及微生态

以经过厌氧反应器处理后的猪场废水为研究对象,探讨了新型生态高负荷土地快速渗滤系统对废水中COD、氨氮及总氮的去除情况;同时分析了该系统中的微生物群落结构以及过氧化氢酶、脲酶、硝酸盐还原酶的含量.结果表明,在水力负荷为11 cm·d~(-1)、进水COD为700 mg·L~(-1)左右的条件下,一级土地渗滤柱与二级土地渗滤柱对COD的去除率分别为78.8%与63.0%,总去除率达到了92.6%;而当水力负荷增大到22 cm·d~(-1)时,总的COD去除率仍在90.0%以上;该系统对于氨氮的去除更为显著,去除率可达99%左右.一级土地快速渗滤系统中上、中、下部的过氧化氢酶含量分别为1.899、0.990、0.323 m L·g~(-1),表明猪场废水中的有机物主要在该系统的上部与中部得以去除;二级土地快速渗滤系统上、中、下部的硝酸盐还原酶含量分别是3.453、3.831、1.971 m L·g~(-1),表明脱氮作用主要发生二级土地快速渗滤系统的上部与中部.该土地快速渗滤系统中微生物以Gram Negative与Gram Positive为主,特别是在二级土地快速渗滤系统中,AM Fungi与Actinomycetes占有一定比例,为猪场废水中难降解有机物的去除提供了保障.     

海水生物滤器氨氮沿程转化规律模型

生物滤器是海水循环水养殖系统中的核心水处理单元,其主要用于去除对养殖生物有害的氨氮、有机物等.本研究基于吸附原理和一级反应生物膜理论构建了氨氮在生物滤器中沿程转化规律的数学模型,并通过实验加以验证.实验所用生物滤器采用竹制空心生化球填料,装填高度为70 cm,在pH为7.1～7.6,DO为5～7 mg.L-1,气水比20∶1左右,有机负荷约为4g.(m3.h)-1,水力停留时间(HRT)为1 h条件下,生物滤器中氨氮的去除主要发生在填料高度0～10 cm处,10～70 cm处氨氮去除量很少.进水氨氮质量浓度的增大和水力停留时间的降低都会导致出水氨氮质量浓度增大.此外,模型对进水氨氮质量浓度较低时的沿程出水氨氮质量浓度具有很好的预测效果;当进水氨氮质量浓度较高时,预测值略低于实际结果.     

人工湿地净化海水养殖外排水影响因素与效果实验研究

以海水养殖外排水为处理对象,构建芦苇复合垂直流人工湿地模拟系统进行处理效果的影响因素(盐度,水力负荷,污染负荷)实验。植物选择芦苇,种植密度为48株/m2,基质填料选择细纱、蛭石、高炉矿渣、沸石和砾石。实验结果显示,随着盐度的升高,人工湿地对CODMn和NH4-N的去除率差异不显著(P>0.05),对PO4-P的去除率在逐渐降低,变化显著(P<0.05),但芦苇表现出较强的耐盐性,在盐度20时生长良好。随着水力负荷的增加,人工湿地对CODMn、NH4-N和PO4-P的去除率呈现出降低的趋势,变化显著(P<0.05);而当污染负荷增加时,去除率呈现出先增加后降低的趋势。综合考虑运行合理性及运行效果,得出合理工况为盐度20,水力负荷0.4 m3/(m2.d),污染负荷CODMn 10 mg/L,NH4-N 2 mg/L,PO4-P 0.5 mg/L。在此工况下,系统稳定运行2个月,显示人工湿地对海水养殖外排水中的污染物具有较好的去除效果。     

有实效性选择过喷漆废水处理药剂的简易方式

随着油漆的多样化,在喷涂过程中产生的过喷漆废水中含有的油漆种类也随之增加和变化。在众多的试剂产品中,寻找出有效的处理过喷漆废水的药剂,显得尤为重要。因此为了使实验结论等同于实际运行结果,经过多种模拟实验和实际运行的对比,总结出了适合现场简易操作的实验方法,可有效提前预料实际运行效果。     

Emissions of SO2, NO and N2O in a circulating fluidized bed combustor during co-firing coal and biomass

This paper presents the experimental investigations of the emissions of SO2, NO and N2O in a bench scale circulating fluidized bed combustor for coal combustion and co-firing coal and biomass. The thermal capacity of the combustor is 30 kW. The setup is electrically heated during startup. The influence of the excess air, the degree of the air staging, the biomass share and the feeding position of the fuels on the emissions of SO2, NO and N2O were studied. The results showed that an increase in the biomass shares resulted in an increase of the CO concentration in the flue gas, probably due to the high volatile content of the biomass. In co-firing, the emission of SO2 increased with increasing biomass share slightly, however, non-linear increase relationship between SO2 emission and fuel sulfur content was observed. Air staging significantly decreased the NO emission without raising the SO2 level. Although the change of the fuel feeding position from riser to downer resulted in a decrease in the NO emission level, no obvious change was observed for the SO2 level. Taking the coal feeding position R as a reference, the relative NO emission could significantly decrease during co-firing coal and biomass when feeding fuel at position D and keeping the first stage stoichiometry greater than 0.95. The possible mechanisms of the sulfur and nitrogen chemistry at these conditions were discussed and the ways of simultaneous reduction of SO2, NO and N2O were proposed.     

不同雨强条件下太湖流域典型蔬菜地土壤磷素的径流特征

以太湖流域典型区域无锡市近郊区鸿声镇的蔬菜地为研究对象,采用人工模拟降雨的方法,通过野外径流小区试验,研究了不同雨强对菜地土壤磷素径流流失的影响.结果表明,初始产流时间随雨强的增大呈幂函数减小(R²=0.99),径流量在雨强较小时,缓慢上升,但随着雨强的增大急剧上升,在雨强0.83、1.17和1.67 mm·min^-1时,总磷(TP)和颗粒态磷(PP)都表现为初始流失浓度较高,随降雨历时延长略有下降,最终趋于稳定,而在大雨强2.50 mm·min^-1时,TP和PP呈现波浪式起伏,没有明显的变化趋势;在整个降雨-径流过程中,溶解态磷(DP)变化比较平缓,占TP的比例为20%～32%,而PP占TP的比例为68%～80%,其变化规律与TP相一致,由此可见,PP是土壤磷素流失的主要形态;通过对比不同雨强下不同形态磷素的流失率,发现TP的流失率,大雨强2.50 mm·min^-1是小雨强0.83 mm·min^-1的20倍,而DP的流失率,却是33倍,这表明随着雨强的增加,加速土壤PP流失的同时,也大大促进了DP的流失,主要原因是降雨前表施磷肥,使得磷肥中大量的无机态磷溶解释放到水环境中,增加了DP的流失,从而会加重受纳水体富营养化的程度.     

Anaerobic tapered fluidized bed reactor for starch wastewater treatment and modeling using multilayer perceptron neural network

Anaerobic treatability of synthetic sago wastewater was investigated in a laboratory anaerobic tapered fluidized bed reactor(ATFBR) with a mesoporous granular activated carbon(GAC)as a support material.The experimental protocol was defined to examine the effect of the maximum organic loading rate(OLR),hydraulic retention time(HRT),the efficiency of the reactor and to report on its steady- state performance.The reactor was subjected to a steady-state operation over a range of OLR up to 85.44 kg COD/(m~3.d).The COD removal efficiency was found to be 92% in the reactor while the biogas produced in the digester reached 25.38 m~3/(m~3·d) of the reactor. With the increase of OLR from 83.7 kg COD/(m~3.d),the COD removal efficiency decreased.Also an artificial neural network(ANN) model using multilayer perceptron(MLP)has been developed for a system of two input variable and five output dependent variables. For the training of the input-output data,the experimental values obtained have been used.The output parameters predicted have been found to be much closer to the corresponding experimental ones and the model was validated for 30% of the untrained data.The mean square error(MSE)was found to be only 0.0146.     

空调系统冷冻水循环水泵变频运行的变温差控制

在分析空调系统变流量运行调节的基础上,提出了变温差控制并给出了控制方案。变温差控制过程不仅具有负反馈,而且具有正反馈,能较好的适应空调负荷的变化。比较分析了变温差控制、定温差控制、定压差控制的节能性,变温差控制的节能潜力最大,是一种最佳控制方式。     

卫生填埋场黏土衬层密实性试验研究

开展卫生填埋场中的黏土衬层密实性试验研究对填埋场的工程设计和后期运营具有现实意义.黏土压实的直接影响之一就是孔隙率的减小,并改变黏土的电阻率,为高密度电阻率法在衬层密实性中的调查研究提供了前提条件和物理基础.文章采用高密度电阻率法三种装置(测深、温纳、偶极-偶极)进行对比测量,通过电阻率成像技术对压实黏土的电性特征进行...