Performance of ANFIS versus MLP-NN dissolved oxygen prediction models in water quality monitoring

We discuss the accuracy and performance of the adaptive neuro-fuzzy inference system (ANFIS) in training and prediction of dissolved oxygen (DO) concentrations. The model was used to analyze historical data generated through continuous monitoring of water quality parameters at several stations on the Johor River to predict DO concentrations. Four water quality parameters were selected for ANFIS modeling, including temperature, pH, nitrate (NO₃) concentration, and ammoniacal nitrogen concentration (NH₃-NL). Sensitivity analysis was performed to evaluate the effects of the input parameters. The inputs with the greatest effect were those related to oxygen content (NO₃) or oxygen demand (NH₃-NL). Temperature was the parameter with the least effect, whereas pH provided the lowest contribution to the proposed model. To evaluate the performance of the model, three statistical indices were used: the coefficient of determination (R ²), the mean absolute prediction error, and the correlation coefficient. The performance of the ANFIS model was compared with an artificial neural network model. The ANFIS model was capable of providing greater accuracy, particularly in the case of extreme events.     

淄博市某城市污水处理厂运行效果分析

淄博市是我国重要的石油化工基地,工业废水与生活污水多混合排放到城市污水处理厂处理,污水成分复杂,处理难度大。根据淄博市某污水处理厂的长期运行数据,评价了悬浮性固体(SS)、化学需氧量(COD)、五日生化需氧量(BOD5)、氨氮(NH3-N)和总磷(TP)等水质指标的去除效果。结果表明:该厂实际水量高于设计水量,处于超负荷运行状态,且进水SS浓度较高,BOD5/COD2O工艺,设计停留时间较长,并将二沉池污泥部分回流到初沉池,提高对污染物去除效果,使出水SS、COD、BOD5、NH3-N和TP等指标达到一级A排放标准。进水中偶尔含有冲击性高浓度挥发酚,使污水厂硝化菌功能受抑制,出水NH3-N浓度异常升高,此时该厂通过投加活性污泥进行硝化菌接种,帮助系统尽快恢复正常运行;同时,高盐度工业废水会加速污水厂设备腐蚀。     

化学强化-复合人工湿地组合工艺对东莞运河污水的处理效果

通过采用混凝法的化学强化预处理单元和以水平潜流-折流型潜流复合人工湿地作为后续深度处理单元,对东莞运河进行了为期半年以上的示范工程运行实验研究。实验结果表明,经过化学强化法的作用,去除了大量的颗粒悬浮物,对进水水体中的COD、BOD5和TP有明显去除,其去除率分别为28.23%、20.65%和30.41%~72.16%,但对NH4+-N、TN的处理不够理想;经过复合人工湿地后COD、BOD5、TP、NH4+-N和TN的总去除率分别达到65.53%、57.55%、88.66%、60.94%和29.48%,说明该组合工艺对COD、BOD5、TP和NH4+-N均有较好的处理效果,但对TN的去除率仍不高,主要原因是湿地系统溶解氧较高,限制了反硝化去除TN的作用。从总体处理效果来看,化学强化-复合人工湿地组合工艺对东莞运河污水有良好的处理效果,具有广阔的应用前景。     

Application of a constructed wetland for industrial wastewater treatment: a pilot-scale study

The main objective of this study was to examine the efficacy and capacity of using constructed wetlands on industrial pollutant removal. Four parallel pilot-scale modified free water surface (FWS) constructed wetland systems [dimension for each system: 4-m (L)x1-m (W)x1-m (D)] were installed inside an industrial park for conducting the proposed treatability study. The averaged influent contains approximately 170 mg l(-1) chemical oxygen demand (COD), 80 mg l(-1) biochemical oxygen demand (BOD), 90 mg l(-1) suspend solid (SS), and 32 mg l(-1) NH(3)-N. In the plant-selection study, four different wetland plant species including floating plants [Pistia stratiotes L. (P. stratiotes) and Ipomoea aquatica (I. aquatica)] and emergent plants [Phragmites communis L. (P. communis) and Typha orientalis Presl. (T. orientalis)] were evaluated. Results show that only the emergent plant (P. communis) could survive and reproduce with a continuous feed of 0.4m(3)d(-1) of the raw wastewater. Thus, P. communis was used in the subsequent treatment study. Two different control parameters including hydraulic retention time (HRT) (3, 5, and 7d) and media [vesicles ceramic bioballs and small gravels, 1cm in diameter] were examined in the treatment study. Results indicate that the system with a 5-d HRT (feed rate of 0.4m(3)d(-1)) and vesicles ceramic bioballs as the media had the acceptable and optimal pollutant removal efficiency. If operated under conditions of the above parameters, the pilot-plant wetland system can achieve removal of 61% COD, 89% BOD, 81% SS, 35% TP, and 56% NH(3)-N. The treated wastewater meets the current industrial wastewater discharge standards in Taiwan.     

臭氧气浮工艺处理城市合流制溢流污染

合流制溢流(CSO)污水具有水质水量波动大、非连续产生的特点,采用臭氧气浮技术对CSO污水进行处理,研究该技术对化学需氧量(COD)、总磷(TP)、悬浮固体(SS)等污染指标的控制效果。实验室小试结果表明,在最适工艺条件下,混凝-臭氧同步处理对CSO实际污水SS、TP、COD去除率分别为77.8%、73.6%和57.9%,显著削弱了腐殖质类有机物荧光强度,混凝与臭氧氧化之间表现出良好的协同作用,能够实现CSO污染的有效控制。进一步设计了臭氧气浮撬装式设备,并在武汉市开展了CSO处理现场实验研究,运行结果表明,臭氧气浮工艺系统对SS、TP、COD的平均去除率分别为81.8%、75.4%和61.7%,净化效果良好,实现了对CSO典型污染物的协同治理。通过实验室研究和工程实验结果,证实了臭氧气浮工艺用于CSO污水治理的工程可行性,上述研究结果可为CSO污水的多水质目标协同控制提供理论指导和技术参考。     

水景间歇复氧条件下护岸型湿地的水质净化效率

为改善缓流景观水体水质,通过搭建小试实验装置,研究了曝气处理、喷泉处理和跌水处理对护岸型湿地中污染物去除率的影响。结果表明,在水力停留时间（HRT）为4 d时,护岸型湿地对缓流景观水体中的总磷（TP）、总氮（TN）和化学需氧量（COD）平均去除率分别达到了48.63%、43.41%和68.51%;3组处理系统均通过间歇复氧促进了护岸型湿地对氮磷的去除,与空白处理相比,曝气处理、喷泉处理及跌水处理使得TP的去除率分别提高了13.59%、11.12%和14.42%,TN的去除率分别提高了10.32%、13.13%和8.88%,COD的去除率提高了24.82%、24.60%和23.09%;同时发现,4个处理系统对氮磷的去除率随温度的下降而降低。     

The potential use of constructed wetlands in a recirculating aquaculture system for shrimp culture

A pilot-scale constructed wetland unit, consisting of free water surface (FWS) and subsurface flow (SF) constructed wetlands arranged in series, was integrated into an outdoor recirculating aquaculture system (RAS) for culturing Pacific white shrimp (Litopenaeus vannamei). This study evaluated the performance of the wetland unit in treating the recirculating wastewater and examined the effect of improvement in water quality of the culture tank on the growth and survival of shrimp postlarvae. During an 80-day culture period, the wetland unit operated at a mean hydraulic loading rate of 0.3 m/day and effectively reduced the influent concentrations of 5-day biochemical oxygen demand (BOD5, 24%), suspended solids (SS, 71%), chlorophyll a (chl-a, 88%), total ammonium (TAN, 57%), nitrite nitrogen (NO2-N, 90%) and nitrate nitrogen (NO3-N, 68%). Phosphate (PO4-P) reduction was the least efficient (5.4%). The concentrations of SS, Chl-a, turbidity and NO3-N in the culture tank water in RAS were significantly (P相似文献   

人工河岸湿地对面源污染的处理效果研究

针对城市河道污染治理存在的主要问题,并考虑到华南地区河流水量、水质、水温季节性变化大的特点,构筑了人工河岸湿地试验系统,对该系统约13个月连续性运行进行了观测和研究。结果表明,平均水力负荷为15cm/d工况下,试验系统对高锰酸盐指数、SS、NH3-N、TN和TP的平均去除率分别为50%、60%、50%、35%和45%;系统对高锰酸盐指数、NH3-N和TN的去除效果随季节变化明显,夏季处理效果好于冬季;SS处理效果受季节影响不明显;TP初期处理效果好于末期。该人工河岸湿地既能较好地改善水质,又能改善生态环境、美化城市景观,是一项适合城市河道污染治理的技术。     

城市湿地景观水体富营养化评价、机理及治理

针对再生水回用的景观水体容易发生富营养化的问题,分别以再生水和径流雨水为主要补水水源的某城市湿地不同区域景观水体为研究对象,通过水体TN、TP、COD、SS、Chla、DO等水质指标检测分析,研究了污染物的空间变化和季节变化规律,评价了湿地水体富营养化程度并探讨其机理。结果表明,以再生水为主要补水水源的湿地水体全部呈现中度富营养,而以径流雨水为主要补水水源的湿地水体则整体呈现中营养。湿地生态系统对再生水输入的高浓度氮磷污染物有一定的净化效果,但净化效率有限且受季节因素影响明显,藻类的季节性增殖引起水体中TN、TP浓度降低、SS降低、透明度下降和COD浓度升高,高浓度氮磷营养盐输入是湿地水体藻类增殖并呈现富营养化的主要原因。提出了再生水补水的水质和水量控制、景观水体健康生态系统的构建和水体长期的维护管理是综合治理水体富营养化的有效对策。     

紫外-近红外光谱法测定废水COD含量

针对传统方法测定化学需氧量（COD）药剂成本高、检测效率低、连续监测难、废液二次污染等问题,基于现有的紫外-可见光与近红外光谱法测量COD技术,研究了综合利用紫外光谱与近红外光谱中的信息来预测废水中COD含量的可行性。实验采集了100个工厂现场水样,每一水样分成两组：一组测其190~2 300 nm波长范围的光谱数据,另一组利用传统方法测其COD,并把该方法得到的结果作为标定该水样光谱的标准值,对水样光谱用偏最小二乘法（PLS）建立废水样的COD预测模型。经验证预测值与实测值的相关度为0.967 1,验证标准误差值为24.8 mg·L-1,具有较好的预测效果。     

不同填料在折流湿地中脱氮除磷的动力学分析

为了解决我国西部农村分散式生活污水污染问题,结合西北地区年平均气温条件特征,基于潜流湿地原理对比研究了混凝土渣、砾石和生物炭脱氮除磷效应,分析其对污染物的降解作用。结果表明：随着水力停留时间(HRT)的延长,污染物含量明显降低,湿地最佳HRT均为2.5 d,3种填料湿地对化学需要量(COD)、氨氮(${ {\rm{NH}}_{\rm{4}}^{\rm{ + }}}$-N)、磷酸盐(${ {\rm{PO}}_{\rm{4}}^{{\rm{3 - }}}}$-P)的去除效果差异性显著(P<0.01);混凝土渣对污水中${ {\rm{PO}}_{\rm{4}}^{{\rm{3 - }}}}$-P的去除最优,去除率为97.11%;生物炭综合处理能力较强,COD、${ {\rm{NH}}_{\rm{4}}^{\rm{ + }}}$-N、悬浮物(SS)的去除率达到了90.51%、72.38%、94.57%;生物炭作为优选湿地填料还具有较快的污染物降解速率特征,且有机污染物和磷酸盐的生化降解过程符合一级反应动力学模型,R²在0.9以上。因此,生物炭作为湿地填料具有良好的应用价值,对解决西北地区农村水污染问题具有重要的意义。     

River water quality assessment using environmentric techniques: case study of Jakara River Basin

Jakara River Basin has been extensively studied to assess the overall water quality and to identify the major variables responsible for water quality variations in the basin. A total of 27 sampling points were selected in the riverine network of the Upper Jakara River Basin. Water samples were collected in triplicate and analyzed for physicochemical variables. Pearson product-moment correlation analysis was conducted to evaluate the relationship of water quality parameters and revealed a significant relationship between salinity, conductivity with dissolved solids (DS) and 5-day biochemical oxygen demand (BOD₅), chemical oxygen demand (COD), and nitrogen in form of ammonia (NH₄). Partial correlation analysis (r _p) results showed that there is a strong relationship between salinity and turbidity (r _p?=?0.930, p?=?0.001) and BOD₅ and COD (r _p?=?0.839, p?=?0.001) controlling for the linear effects of conductivity and NH₄, respectively. Principal component analysis and or factor analysis was used to investigate the origin of each water quality parameter in the Jakara Basin and identified three major factors explaining 68.11 % of the total variance in water quality. The major variations are related to anthropogenic activities (irrigation agricultural, construction activities, clearing of land, and domestic waste disposal) and natural processes (erosion of river bank and runoff). Discriminant analysis (DA) was applied on the dataset to maximize the similarities between group relative to within-group variance of the parameters. DA provided better results with great discriminatory ability using eight variables (DO, BOD₅, COD, SS, NH₄, conductivity, salinity, and DS) as the most statistically significantly responsible for surface water quality variation in the area. The present study, however, makes several noteworthy contributions to the existing knowledge on the spatial variations of surface water quality and is believed to serve as a baseline data for further studies. Future research should therefore concentrate on the investigation of temporal variations of water quality in the basin.     

On-site phytoremediation applicability assessment in Alur Ilmu,Universiti Kebangsaan Malaysia based on spatial and pollution removal analyses

The present paper aims to assess the phytoremediation performance based on pollution removal efficiency of the highly polluted region of Alur Ilmu urban river for its applicability of on-site treatment. Thirteen stations along Alur Ilmu were selected to produce thematic maps through spatial distribution analysis based on six water quality parameters of Malaysia’s Water Quality Index (WQI) for dry and raining seasons. The maps generated were used to identify the highly polluted region for phytoremediation applicability assessment. Four free-floating plants were tested in treating water samples from the highly polluted region under three different conditions, namely controlled, aerated and normal treatments. The selected free-floating plants were water hyacinth (Eichhornia crassipes), water lettuce (Pistia stratiotes), rose water lettuce (Pistia sp.) and pennywort (Centella asiatica). The results showed that Alur Ilmu was more polluted during dry season compared to raining season based on the water quality analysis. During dry season, four parameters were marked as polluted along Alur Ilmu, namely dissolve oxygen (DO), 4.72 mg/L (class III); ammoniacal nitrogen (NH₃–N), 0.85 mg/L (class IV); total suspended solid (TSS), 402 mg/L (class V) and biological oxygen demand (BOD), 3.89 mg/L (class III), whereas, two parameters were classed as polluted during raining season, namely total suspended solid (TSS), 571 mg/L (class V) and biological oxygen demand (BOD), 4.01 mg/L (class III). The thematic maps generated from spatial distribution analysis using Kriging gridding method showed that the highly polluted region was recorded at station AL 5. Hence, water samples were taken from this station for pollution removal analysis. All the free-floating plants were able to reduce TSS and COD in less than 14 days. However, water hyacinth showed the least detrimental effect from the phytoremediation process compared to other free-floating plants, thus made it a suitable free-floating plants to be used for on-site treatment.     

Solid waste forecasting using modified ANFIS modeling

Solid waste prediction is crucial for sustainable solid waste management. Usually, accurate waste generation record is challenge in developing countries which complicates the modelling process. Solid waste generation is related to demographic, economic, and social factors. However, these factors are highly varied due to population and economy growths. The objective of this research is to determine the most influencing demographic and economic factors that affect solid waste generation using systematic approach, and then develop a model to forecast solid waste generation using a modified Adaptive Neural Inference System (MANFIS). The model evaluation was performed using Root Mean Square Error (RMSE), Mean Absolute Error (MAE) and the coefficient of determination (R2). The results show that the best input variables are people age groups 0-14, 15-64, and people above 65 years, and the best model structure is 3 triangular fuzzy membership functions and 27 fuzzy rules. The model has been validated using testing data and the resulted training RMSE, MAE and R2 were 0.2678, 0.045 and 0.99, respectively, while for testing phase RMSE =3.986, MAE = 0.673 and R2 = 0.98.

Implications: To date, a few attempts have been made to predict the annual solid waste generation in developing countries. This paper presents modeling of annual solid waste generation using Modified ANFIS, it is a systematic approach to search for the most influencing factors and then modify the ANFIS structure to simplify the model. The proposed method can be used to forecast the waste generation in such developing countries where accurate reliable data is not always available. Moreover, annual solid waste prediction is essential for sustainable planning.     

Advanced extraction and lower bounds for removal of pollutants from wastewater by water plants.

The capacity to reach lower bounds for extraction of pollutants from wastewater by four floating aquatic macrophytes--water hyacinth (Eichhornia crassipes), water lettuce (Pistia stratiotes), salvinia (Salvinia rotundifolia), and water primroses (Ludvigia palustris)--is investigated. It is shown that the following lower bounds can be established for wastewater purification with water hyacinth: biochemical oxygen demand (BOD), 1.3 mg/L; chemical oxygen demand (COD), 11.3 mg/L; total suspended solids (TSS), 0.5 mg/L; turbidity, 0.7 NTU; ammonia, 0.2 mg/L; and phosphorus, 1.4 mg/L. Also, the following lower bounds can be established for wastewater purification with water lettuce: BOD, 1.8 mg/L; COD, 12.5 mg/L; TSS, 0.5 mg/L; turbidity, 0.9 NTU; ammonia, 0.2 mg/L; and phosphorus, 1.6 mg/L. These lower bounds were reached in 11- to 17-day experiments that were performed on diluted wastewater with reduced initial contents of the tested water quality indicators. As expected, water hyacinth exhibited the highest rates and levels of pollutant removal, thereby producing the best lower bounds of the water quality indicators. Given the initially low levels, BOD was further reduced by 86.3%, COD by 66.6%, ammonia by 97.8%, and phosphorus by 65.0% after 11 days of a batch experiment. The capacity of water plants to purify dilute wastewater streams opens new options for their application in the water treatment industry.     

运河(杭州段)沉积物耗氧物质释放的模拟实验研究

通过室内模拟试验研究了运河 (杭州段 )沉积物污染引起的上覆水 CO DCr的变化 ,并研究了连续曝气、换水清洗的方法对其耗氧物质释放的影响。结果发现由于沉积物的释放使得上覆水 CODCr浓度维持在劣四类水以上。连续曝气可以降低水体的恶臭 ,但由于曝气对沉积物的扰动引起沉积物更多地再悬浮 ,上覆水 CODC r也没有明显降低。在不考虑外源影响的情况下 ,换水清洗可以将上覆水 CODCr浓度降到 30 m g· L-1以下。本研究说明运河 (杭州段 )沉积物内源释放对上覆水 CODCr有较大的影响。     

感潮平原中心城区河道近自然生态修复技术的应用

针对感潮平原中心城区河道存在往复流现象带来的水质波动、生态岸线差、生态系统稳定性不足等问题,开展以基于生物屏障技术耦合水生动植物生态系统构建为主的全面系统的近自然生态修复集成技术及示范研究。注重源头削减和末端综合治理,通过集成构建河道水质稳定技术、海绵设施生态岸线、优化水生态系统措施等技术体系,并选取上海市中心城区典型河道进行示范应用及效果跟踪。结果表明,修复后河道水质和感官效果得到了极大提升,化学需氧量(COD)、氨氮、总磷、浊度/悬浮物(SS)各均值较未处理河道水质均值分别降低约23%、41%、35%、51%/52%,5大类抗生素除了洁霉素、克林霉素和磺胺吡啶外均未检出,河道水质从在地表水IV类水质上下波动稳定达到IV类(总氮指标除外)。     

Absorption and fluorescence properties of chromophoric dissolved organic matter: implications for the monitoring of water quality in a large subtropical reservoir

The development of techniques for real-time monitoring of water quality is of great importance for effectively managing inland water resources. In this study, we first analyzed the absorption and fluorescence properties in a large subtropical reservoir and then used a chromophoric dissolved organic matter (CDOM) fluorescence monitoring sensor to predict several water quality parameters including the total nitrogen (TN), total phosphorus (TP), chemical oxygen demand (COD), dissolved organic carbon (DOC), and CDOM fluorescence parallel factor analysis (PARAFAC) components in the reservoir. The CDOM absorption coefficient at 254 nm (a(254)), the humic-like component (C1), and the tryptophan-like component (C3) decreased significantly along a gradient from the northwest to the lake center, northeast, southwest, and southeast region in the reservoir. However, no significant spatial difference was found for the tyrosine-like component (C2), which contributed only four marked peaks. A highly significant linear correlation was found between the a(254) and CDOM concentration measured using the CDOM fluorescence sensor (r ²?=?0.865, n?=?76, p?相似文献   

水深对表面流人工湿地污染河水处理系统运行效果的影响

基于中试系统一年的连续运行监测,研究了水深对芦苇表面流人工湿地污染河水处理系统的影响。结果表明,水深对表面流人工湿地污染河水处理系统运行效果有很大影响,在进水COD、氨氮、总氮和总磷等分别为36±4.46、0.92±0.47、6.27±2.01和0.13±0.05 mg/L条件下,水深50 cm时处理效果最好,COD、氨氮、总氮和总磷去除率分别达到42.75%、58.42%、56.94%和43.24%。综合污染物去除效果和人工湿地建设工程量,芦苇表面流人工湿地的水深宜采用50 cm。人工湿地系统中植物光合生理和溶解氧等研究表明,水深主要通过影响植物生长和溶解氧等而影响人工湿地的水质净化效果。     

复合人工湿地对城市受污染河水的净化效果

采用2种复合人工湿地系统处理昆明市城市河流污水,为期1年的运行结果表明:2种复合人工湿地系统对城市河流污水具有良好的污染物去除性能,TN、TP、COD和SS的月平均去除率分别达到50%、85%、85%和80%以上;2种复合人工湿地系统具有良好的耐冲击性,季节变化对出水水质不存在显著影响。其中,垂直上行流复合人工湿地系统性能更优于垂直上行流与水平流复合人工湿地系统;强降雨会对复合人工湿地出水水质造成一定的影响。