Modeling of a sequencing batch reactor treating municipal wastewater using multi-layer perceptron and radial basis function artificial neural networks

A sequencing batch reactor was modeled using multi-layer perceptron and radial basis function artificial neural networks (MLPANN and RBFANN). Then, the effects of influent concentration (IC), filling time (FT), reaction time (RT), aeration intensity (AI), SRT and MLVSS concentration were examined on the effluent concentrations of TSS, TP, COD and NH₄⁺-N. The results showed that the optimal removal efficiencies would be obtained at FT of 1 h, RT of 6 h, aeration intensity of 0.88 m³/min and SRT of 30 days. In addition, COD and TSS removal efficiencies decreased and TP and NH₄⁺-N removal efficiencies did not change significantly with increases of influent concentration. The TSS, TP, COD and NH₄⁺-N removal efficiencies were 86%, 79%, 94% and 93%, respectively. The training procedures of all contaminants were highly collaborated for both RBFANN and MLPANN models. The results of training and testing data sets showed an almost perfect match between the experimental and the simulated effluent of TSS, TP, COD and NH₄⁺-N. The results indicated that with low experimental values of input data to train ANNs the MLPANN models compared to RBFANN models are more precise due to their higher coefficient of determination (R²) and lower root mean squared errors (RMSE) values.     

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.     

Neural network forecasting of air pollutants hourly concentrations using optimised temporal averages of meteorological variables and pollutant concentrations

The new method for the forecasting hourly concentrations of air pollutants is presented in the paper. The method was developed for a site in urban residential area in city of Zagreb, Croatia, for four air pollutants (NO₂, O₃, CO and PM₁₀). Meteorological variables and concentrations of the respective pollutant were taken as predictors. A novel approach, based on families of univariate regression models, was employed in selecting the averaging intervals for input variables. For each variable and each averaging period between 1 and 97 h, a separate model was built. By inspecting values of the coefficient of correlation between measured and modelled concentrations, optimal averaging periods for each variable were selected. A new dataset for building the forecasting model was then calculated as temporal moving averages (running means) of former variables. A multi-layer perceptron type of neural networks is used as the forecasting model. Index of agreement, calculated for the entire dataset including the data for model building, ranged from 0.91 to 0.97 for the respective pollutants. As suggested by the analysis of the relative importance of the input variables, different agreements for different pollutants are likely due to different sources and production mechanisms of investigated pollutants. A comparison of the new method with more traditional method, which takes hourly averages of the forecast hour as input variables, showed similar or better performance. The model was developed for the purpose of public-health-oriented air quality forecasting, aiming to use a numerical weather forecast model for the prediction of the part of input data yet unknown at the forecasting time. It is to expect that longer term averages used as inputs in the proposed method will contribute to smaller input errors and the greater accuracy of the model.     

Pipeline leakage detection and isolation: An integrated approach of statistical and wavelet feature extraction with multi-layer perceptron neural network (MLPNN)

Leakage diagnosis of hydrocarbon pipelines can prevent environmental and financial losses. This work proposes a novel method that not only detects the occurrence of a leakage fault, but also suggests its location and severity. The OLGA software is employed to provide the pipeline inlet pressure and outlet flow rates as the training data for the Fault Detection and Isolation (FDI) system. The FDI system is comprised of a Multi-Layer Perceptron Neural Network (MLPNN) classifier with various feature extraction methods including the statistical techniques, wavelet transform, and a fusion of both methods. Once different leakage scenarios are considered and the preprocessing methods are done, the proposed FDI system is applied to a 20-km pipeline in southern Iran (Goldkari-Binak pipeline) and a promising severity and location detectability (a correct classification rate of 92%) and a low False Alarm Rate (FAR) were achieved.     

Progress in developing an ANN model for air pollution index forecast

An air pollution index (API) reporting system is introduced to selected cities of China for public communication on air quality data. Shanghai is the first city in China providing daily average API reports and forecasts. This paper describes the development of an artificial neural network (ANN) model for the API forecasting in Shanghai. It is a multiple layer perceptron (MLP) network, with meteorological forecasting data as the main input, to output the next day average API values. However, the initial version of the MLP model did not work well. To improve the model, a series of tests were conducted with respect to the training method and structure optimization. Based on the test results, the training algorithm was modified and a new model was built. The new model is now being used in Shanghai for API forecasting. Its performance is shown reasonably well in comparison with observation. The application of the old model was only weakly correlated with observation. In 1-year application, the correlation coefficients were 0.2314, 0.1022 and 0.1710 for TSP, SO₂ and NO_x, respectively. But for the new model, for over 8 months application, the correlation coefficients are raised to 0.6056, 0.6993 and 0.6300 for PM₁₀, SO₂, and NO₂. Further, the new algorithm does not rely on manpower intervention so that it is now being applied in several other Chinese cities with quite different meteorological conditions. The structure of the model and the application results are presented in this paper and also the problems to be further studied.     

Characterization of humic substances of different origin by means of mass spectrometry and neural networks

Mass spectrometry fingerprinting of humic acids extracted from different soils has been carried out using laser desorption/ionization mass spectrometry (LDI-TOF MS). LDI-TOF MS provides characteristic mass spectra fingerprints for the humic acids of different origin. The information given in the fingerprints was evaluated for natural grouping trends in the samples by neural networks computing tools, such as self-organizing feature map (SOFM). This approach is efficient for recognizing patterns in the humic acids samples independently of their characteristic variability; variability characterizing natural products such as humic substances. The use of multi-layer perceptron artificial neural networks gave a successful classification of the samples.     

河道污染质垂向迁移对地下水影响的研究

包气带是连接地表水和地下水的重要通道,对地下水资源有很好的"屏障"功能,而近年来工农业废水及生活污水的大量排放已影响到了地下水的"安全".为此,在渭河河漫滩进行了模拟河流的垂向入渗试验,并通过建立数学模型对水分和六价铬在具有弱透水层的多层介质中的迁移进行了模拟运算.试验和模拟结果一致表明,弱透水层虽对地下水有很好的保护作用,但在上部土壤层易形成面状污染带,而且由于大的浓度梯度作用,一旦污染质穿透该层将很快污染到地下水.     

自然环境因素对铝合金大气腐蚀的影响性研究

目的 研究铝合金大气腐蚀受自然环境因素的影响性，探索环境因素对铝合金腐蚀的影响规律。方法 采用多层感知器神经网络分析环境因素对7种铝合金平均腐蚀速率的影响。结果 确定了影响铝合金腐蚀损伤的重要因素为SO2沉积率、Cl^–沉积率、NOx沉积率；辅要因素为年降雨量、年雾露时数、相对湿度、年日照时数、温度、铝合金成分；次要因素为年累积降水时数、雨水pH值。结论 基于多层感知器神经网络分析有效展现了环境因素对平均腐蚀速率的影响性。     

Air Quality Management in Izmir Region of Turkey as Required by Clean Air Plans

Future (24 h later) daily ground level SO₂ concentration in Istanbul was modeled and predicted using a new and powerful technique, Artificial Neural Networks (ANN) in the case of meteorological parameters as input variables. Results show that the trend of SO₂ from higher values in winter to lower values in spring and summer, and again to higher values towards winter can be correctly represented by the neural networks. The model better predicted the lower SO₂ values in spring and summer seasons when compared to higher values in winter season because of the pattern distribution in training data sets. Beside the amount of the database, the more the variation of the values of the parameters in their own ranges, the more the network learns the database. As a result of this study, considerably successful results were obtained when considering the complex and nonlineer structure of the atmosphere, which is the source of the database.     

Simulation of thermodynamic transmission in green roof ecosystem

Green roofs entail the creation of vegetated space on the top of artificial structures. They can modify the thermal properties of buildings to bring cooling energy conservation and improve human comfort. This study evaluates the thermodynamic transmission in the green roof ecosystem under different vegetation treatments. Our model simulation is based on the traditional Bowen ratio energy balance model (BREBM) and a proposed solar radiation shield effectiveness model (SEM). The BREBM investigates energy absorption of different components of radiation, and the SEM evaluates the radiation shield effects. The proposed model is tested and validated to be efficient to simulate solar energy transmission in green roofs, with some major findings. Firstly, the solar radiation transmission processes might be considered as free vibration motion. Daytime positive heat storage of the green roof is 350-520 W·m⁻² on an hourly basis. Nighttime or afternoon negative value registers a rather constant magnitude of −60 W·m⁻². Daily net average is positive around 155-210 W·m⁻². Secondly, solar radiation vibration is highly correlated with plant structure. The canopy reflectance and transmittance are strongly correlated (R² = 0.87). The multi-layer shrub treatment has the highest shield effectiveness (0.34), followed by two-layer groundcover (0.27), and single-layer grass (0.16). Green roof vegetation absorbs and stores large amounts of heat to form an effective thermal buffer against daily temperature fluctuation. Vegetated roofs drastically depress air temperature in comparison with bare ground (control treatment). Finally, the thermodynamic model is relatively simple and efficient for investigating thermodynamic transmission in green roof ecosystem, and it could be developed into a broad solar radiant land cover model.