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.     

A basic neural traffic noise prediction model for Tehran’s roads

We present an artificial neural network model to predict hourly A-weighted equivalent sound pressure levels (L_Aeq,1h) for roads in Tehran at distances less than 4 m from the nearside carriageway edge. Our model uses the UK Calculation of Road Traffic Noise (CORTN) approach. Data were obtained from 50 sampling locations near five roads in Tehran at nearside carriageway edge distances of less than 4 m. The data were randomly assigned to training, testing, and holdout subsets. Model training was carried out using the training and testing subsets and comprised 60% and 20% of the data, respectively. Model validation was performed using the remaining 20% of data as a holdout subset. We examine the overall model efficiency using non-parametric tests, such as the Wilcoxon matched-pairs signed-rank test for the training step and the Kolmogorov–Smirnov test for two independent samples for the validation step. Our results indicate that a neural network approach can be applied for traffic noise prediction in Tehran in a statistically sound manner. The Wilcoxon matched-pairs signed-ranks test detects no significant difference between the absolute testing set errors of the developed neural network and a calibrated version of the CORTN model.     

MULTITEMPORAL SCALE HYDROGRAPH PREDICTION USING ARTIFICIAL NEURAL NETWORKS1

Abstract: An artificial neural network (ANN) provides a mathematically flexible structure to identify complex nonlinear relationship between inputs and outputs. A multilayer perceptron ANN technique with an error back propagation algorithm was applied to a multitime-scale prediction of the stage of a hydro-logically closed lake, Devils Lake (DL), and discharge of the Red River of the North at Grand Forks station (RR-GF) in North Dakota. The modeling exercise used 1 year (2002), 5 years (1998–2002), and 27 years (1975–2002) of data for the daily, weekly, and monthly predictions, respectively. The hydrometeorological data (precipitations P_(t), P_(t-1), P_(t-2), P_(t-3), antecedent runoff/lake stage R_(t-1) and air temperature T_(t) were partitioned for training and for testing to predict the current hydro-graph at the selected DL and RR-GF stations. Performance of ANN was evaluated using three combinations of daily datasets (Input I = P_(t)), P_(t-l), P_(t-2), P_(t-3), T_(t) and R_(t-l); Input II = Input-l less P_(t) P_(t-l), P_(t-2), P_(t-3); and Input III = Input-II less T_(t)). Comparison of the model output using Input I data with the observed values showed average testing prediction efficiency (E) of 86 percent for DL basin and 46 percent for RR-GF basin, and higher efficiency for the daily than monthly simulations.     

Modeling biological oxygen demand of the Melen River in Turkey using an artificial neural network technique

Artificial neural networks (ANNs) are being used increasingly to predict and forecast water resources' variables. The feed-forward neural network modeling technique is the most widely used ANN type in water resources applications. The main purpose of the study is to investigate the abilities of an artificial neural networks' (ANNs) model to improve the accuracy of the biological oxygen demand (BOD) estimation. Many of the water quality variables (chemical oxygen demand, temperature, dissolved oxygen, water flow, chlorophyll a and nutrients, ammonia, nitrite, nitrate) that affect biological oxygen demand concentrations were collected at 11 sampling sites in the Melen River Basin during 2001-2002. To develop an ANN model for estimating BOD, the available data set was partitioned into a training set and a test set according to station. In order to reach an optimum amount of hidden layer nodes, nodes 2, 3, 5, 10 were tested. Within this range, the ANN architecture having 8 inputs and 1 hidden layer with 3 nodes gives the best choice. Comparison of results reveals that the ANN model gives reasonable estimates for the BOD prediction.     

PREDICTION OF LOCAL SCOUR AROUND BRIDGE PIERS USING ARTIFICIAL NEURAL NETWORKS1

This paper describes a method for predicting local scour around bridge piers using an artificial neural network (ANN). Methods for selecting input variables, calibrations of network control parameters, learning process, and verifications are also discussed. The ANN model trained by laboratory data is applied to both laboratory and field measurements. The results illustrate that the ANN model can be used to predict local scour in the laboratories and in the field better than other empirical relationships that are currently in use. A parameter study is also carried out to investigate the importance of each input variable as reflected in data.     

Comparison of ANN,MVR, and SWR models for computing thermal efficiency of a solar still

In this paper, the viability of modeling the instantaneous thermal efficiency (η_ith) of a solar still was determined using meteorological and operational data with an artificial neural network (ANN), multivariate regression (MVR), and stepwise regression (SWR). This study used meteorological and operational variables to hypothesize the effect of solar still performance. In the ANN model, nine variables were used as input parameters: Julian day, ambient temperature, relative humidity, wind speed, solar radiation, feed water temperature, brine water temperature, total dissolved solids of feed water, and total dissolved solids of brine water. The η_ith was represented by one node in the output layer. The same parameters were used in the MVR and SWR models. The advantages and disadvantages were discussed to provide different points of view for the models. The performance evaluation criteria indicated that the ANN model was better than the MVR and SWR models. The mean coefficient of determination for the ANN model was about 13% and14% more accurate than those of the MVR and SWR models, respectively. In addition, the mean root mean square error values of 6.534% and 6.589% for the MVR and SWR models, respectively, were almost double that of the mean values for the ANN model. Although both MVR and SWR models provided similar results, those for the MVR were comparatively better. The relative errors of predicted η_ith values for the ANN model were mostly in the vicinity of ±10%. Consequently, the use of the ANN model is preferred, due to its high precision in predicting η_ith compared to the MVR and SWR models. This study should be extremely beneficial to those coping with the design of solar stills.     

COMPARISON OF PROCESS‐BASED AND ARTIFICIAL NEURAL NETWORK APPROACHES FOR STREAMFLOW MODELING IN AN AGRICULTURAL WATERSHED1

ABSTRACT: The performance of the Soil and Water Assessment Tool (SWAT) and artificial neural network (ANN) models in simulating hydrologic response was assessed in an agricultural watershed in southeastern Pennsylvania. All of the performance evaluation measures including Nash‐Sutcliffe coefficient of efficiency (E) and coefficient of determination (R²) suggest that the ANN monthly predictions were closer to the observed flows than the monthly predictions from the SWAT model. More specifically, monthly streamflow E and R² were 0.54 and 0.57, respectively, for the SWAT model calibration period, and 0.71 and 0.75, respectively, for the ANN model training period. For the validation period, these values were ?0.17 and 0.34 for the SWAT and 0.43 and 0.45 for the ANN model. SWAT model performance was affected by snowmelt events during winter months and by the model's inability to adequately simulate base flows. Even though this and other studies using ANN models suggest that these models provide a viable alternative approach for hydrologic and water quality modeling, ANN models in their current form are not spatially distributed watershed modeling systems. However, considering the promising performance of the simple ANN model, this study suggests that the ANN approach warrants further development to explicitly address the spatial distribution of hydrologic/water quality processes within watersheds.     

Prediction of global solar radiation using support vector machines

This article utilizes Support Vector Machines (SVM) for predicting global solar radiation (GSR) for Sharurha, a city in the southwest of Saudi Arabia. The SVM model was trained using measured air temperature and relative humidity. Measured data of 1812 values for the period from 1998–2002 were obtained. The measurement data of 1600 were used for training the SVM, and the remaining 212 were used for comparison between the measured and predicted values of GSR. The GSR values were predicted using the following four combinations of data sets: (i) Daily mean air temperature and day of the year as inputs, and global solar radiation as output; (ii) daily maximum air temperature and day of the year as inputs, and GSR as output; (iii) daily mean air temperature and relative humidity and day of the year as inputs, and GSR as output; and (iv) daily mean air temperature, day of the year, relative humidity, and previous day’s GSR as inputs, and GSR as output. The mean square error was found to be 0.0027, 0.0023, 0.0021, and 7.65 × 10^?4 for case (i), (ii,), (iii), and (iv) respectively, while the corresponding absolute mean percentage errors were 5.64, 5.08, 4.48, and 2.8%. Obtained results show that the SVM method is capable of predicting GSR from measured values of temperature and relative humidity.     

LAKE WATER QUALITY ASSESSMENT FROM LANDSAT THEMATIC MAPPER DATA USING NEURAL NETWORK: AN APPROACH TO OPTIMAL BAND COMBINATION SELECTION1

Abstract: The concern about water quality in inland water bodies such as lakes and reservoirs has been increasing. Owing to the complexity associated with field collection of water quality samples and subsequent laboratory analyses, scientists and researchers have employed remote sensing techniques for water quality information retrieval. Due to the limitations of linear regression methods, many researchers have employed the artificial neural network (ANN) technique to decorrelate satellite data in order to assess water quality. In this paper, we propose a method that establishes the output sensitivity toward changes in the individual input reflectance channels while modeling water quality from remote sensing data collected by Landsat thematic mapper (TM). From the sensitivity, a hypothesis about the importance of each band can be made and used as a guideline to select appropriate input variables (band combination) for ANN models based on the principle of parsimony for water quality retrieval. The approach is illustrated through a case study of Beaver Reservoir in Arkansas, USA. The results of the case study are highly promising and validate the input selection procedure outlined in this paper. The results indicate that this approach could significantly reduce the effort and computational time required to develop an ANN water quality model.     

Artificial neural network based maximum power point tracking controller for photovoltaic standalone system

This article presents a two-stage maximum power point tracking (MPPT) controller using artificial neural network (ANN) for photovoltaic (PV) standalone system, under varying weather conditions of solar irradiation and module temperature. At the first-stage, the ANN algorithm locates the maximum power point (MPP) associated to solar irradiation and module temperature. Then, a simple controller at the second-step, by changing the duty cycle of a DC–DC boost converter, tracks the MPP. In this method, in addition to experimental data collection for training the ANN, a circuit is designed in MATLAB-Simulink to acquire data for whole ranges of weather condition. The whole system is simulated in Simulink. Simulation results show small transient response time, and low power oscillation in steady-state. Furthermore, dynamic response verifies that this method is very fast and precise at tracking the MPP under rapidly changing irradiation, and has very low power oscillation under slowly changing irradiation. Experimental results are provided to verify the simulation results as well.     

ANN OUTPUT UPDATING OF LUMPED CONCEPTUAL RAINFALL/RUNOFF FORECASTING MODELS1

ABSTRACT: Artificial neural networks (ANNs) are tested for the output updating of one‐day‐ahead and three‐day‐ahead streamflow forecasts derived from three lumped conceptual rainfall/runoff (R‐R) models: the GR4J, the IHAC, and the TOPMO. ANN output updating proved superior to a parameter updating scheme and to the ‘simple’ output updating scheme, which always replicates the last observed forecast error. In fact, ANN output updating was able to compensate for large differences in the initial performance of the three tested lumped conceptual R‐R models, which the other tested updating approaches were not able to achieve. This is done mainly by incorporating input vectors usually exploited for ANN R‐R modeling such as previous rainfall and streamflow observations, in addition to the previous observed error. For one‐day‐ahead forecasts, the performance of all three lumped conceptual R‐R models, used in conjunction with ANN output updating, was equivalent to that of the ANN R‐R model. For three‐day‐ahead forecasts, the performance of the ANN‐output‐updated conceptual models was even superior to that of the ANN R‐R model, revealing that the conceptual models are probably performing some tasks that the ANN R‐R model cannot map. However, further testing is needed to substantiate the last statement.     

Predicting Carbon Monoxide Concentrations in the Air of Pardis City,Iran, Using an Artificial Neural Network

To date, several methods have been proposed to explain the complex process of air pollution prediction. One of these methods uses neural networks. Artificial neural networks (ANN) are a branch of artificial intelligence, and because of their nonlinear mathematical structures and ability to provide acceptable forecasts, they have gained popularity among researchers. The goal of our study as documented in this article was to compare the abilities of two different ANNs, the multilayer perceptron (MLP) and radial basis function (RBF) neural networks, to predict carbon monoxide (CO) concentrations in the air of Pardis City, Iran. For the study, we used data collected hourly on temperature, wind speed, and humidity as inputs to train the networks. The MLP neural network had two hidden layers that contained 13 neurons in the first layer and 25 neurons in the second layer and reached a mean bias error (MBE) of 0.06. The coefficient of determination (R²), index of agreement (IA), and the Nash–Scutcliffe efficiency (E) between the observed and predicted data using the MLP neural network were 0.96, 0.9057, and 0.957, respectively. The RBF neural network with a hidden layer containing 130 neurons reached an MBE of 0.04. The R², IA, and E between the observed and predicted data using the RBF neural network were 0.981, 0.954, and 0.979, respectively. The results provided by the RBF neural network had greater acceptable accuracy than was the case with the MLP neural network. Finally, the results of a sensitivity analysis using the MLP neural network indicated that temperature is the primary factor in the prediction of CO concentrations and that wind speed and humidity are factors of second and third importance when forecasting CO levels.     

Predicting Debris Yield From Burned Watersheds: Comparison of Statistical and Artificial Neural Network Models1

Abstract: Alluvial fans in southern California are continuously being developed for residential, industrial, commercial, and agricultural purposes. Development and alteration of alluvial fans often require consideration of mud and debris flows from burned mountain watersheds. Accurate prediction of sediment (hyper‐concentrated sediment or debris) yield is essential for the design, operation, and maintenance of debris basins to safeguard properly the general population. This paper presents results based on a statistical model and Artificial Neural Network (ANN) models. The models predict sediment yield caused by storms following wildfire events in burned mountainous watersheds. Both sediment yield prediction models have been developed for use in relatively small watersheds (50‐800 ha) in the greater Los Angeles area. The statistical model was developed using multiple regression analysis on sediment yield data collected from 1938 to 1983. Following the multiple regression analysis, a method for multi‐sequence sediment yield prediction under burned watershed conditions was developed. The statistical model was then calibrated based on 17 years of sediment yield, fire, and precipitation data collected between 1984 and 2000. The present study also evaluated ANN models created to predict the sediment yields. The training of the ANN models utilized single storm event data generated for the 17‐year period between 1984 and 2000 as the training input data. Training patterns and neural network architectures were varied to further study the ANN performance. Results from these models were compared with the available field data obtained from several debris basins within Los Angeles County. Both predictive models were then applied for hind‐casting the sediment prediction of several post 2000 events. Both the statistical and ANN models yield remarkably consistent results when compared with the measured field data. The results show that these models are very useful tools for predicting sediment yield sequences. The results can be used for scheduling cleanout operation of debris basins. It can be of great help in the planning of emergency response for burned areas to minimize the damage to properties and lives.     

APPLICATION OF GREY MODEL AND ARTIFICIAL NEURAL NETWORKS TO FLOOD FORECASTING1

The main focus of this study was to compare the Grey model and several artificial neural network (ANN) models for real time flood forecasting, including a comparison of the models for various lead times (ranging from one to six hours). For hydrological applications, the Grey model has the advantage that it can easily be used in forecasting without assuming that forecast storm events exhibit the same stochastic characteristics as the storm events themselves. The major advantage of an ANN in rainfall‐runoff modeling is that there is no requirement for any prior assumptions regarding the processes involved. The Grey model and three ANN models were applied to a 2,509 km² watershed in the Republic of Korea to compare the results for real time flood forecasting with from one to six hours of lead time. The fifth‐order Grey model and the ANN models with the optimal network architectures, represented by ANN1004 (34 input nodes, 21 hidden nodes, and 1 output node), ANN1010 (40 input nodes, 25 hidden nodes, and 1 output node), and ANN1004T (14 input nodes, 21 hidden nodes, and 1 output node), were adopted to evaluate the effects of time lags and differences between area mean and point rainfall. The Grey model and the ANN models, which provided reliable forecasts with one to six hours of lead time, were calibrated and their datasets validated. The results showed that the Grey model and the ANN1010 model achieved the highest level of performance in forecasting runoff for one to six lead hours. The ANN model architectures (ANN1004 and ANN1010) that used point rainfall data performed better than the model that used mean rainfall data (ANN1004T) in the real time forecasting. The selected models thus appear to be a useful tool for flood forecasting in Korea.     

Spatial Prediction of Ground Subsidence Susceptibility Using an Artificial Neural Network

Ground subsidence in abandoned underground coal mine areas can result in loss of life and property. We analyzed ground subsidence susceptibility (GSS) around abandoned coal mines in Jeong-am, Gangwon-do, South Korea, using artificial neural network (ANN) and geographic information system approaches. Spatial data of subsidence area, topography, and geology, as well as various ground-engineering data, were collected and used to create a raster database of relevant factors for a GSS map. Eight major factors causing ground subsidence were extracted from the existing ground subsidence area: slope, depth of coal mine, distance from pit, groundwater depth, rock-mass rating, distance from fault, geology, and land use. Areas of ground subsidence were randomly divided into a training set to analyze GSS using the ANN and a test set to validate the predicted GSS map. Weights of each factor’s relative importance were determined by the back-propagation training algorithms and applied to the input factor. The GSS was then calculated using the weights, and GSS maps were created. The process was repeated ten times to check the stability of analysis model using a different training data set. The map was validated using area-under-the-curve analysis with the ground subsidence areas that had not been used to train the model. The validation showed prediction accuracies between 94.84 and 95.98%, representing overall satisfactory agreement. Among the input factors, “distance from fault” had the highest average weight (i.e., 1.5477), indicating that this factor was most important. The generated maps can be used to estimate hazards to people, property, and existing infrastructure, such as the transportation network, and as part of land-use and infrastructure planning.     

Predicting Particulate Matter (PM2.5) Concentrations in the Air of Shahr‐e Ray City,Iran, by Using an Artificial Neural Network

Particulate matter (PM), along with other air pollutants, pose serious hazards to human health. The Artificial Neural Network (ANN) is a branch of artificial intelligence that has an ability to make accurate predictions. In this article, the authors describe such methods and how historical data on air quality, moisture, wind velocity, and temperature in Shahr‐e Ray City, located at the southern tip of Tehran, was used to train an ANN to provide accurate predictions of PM concentrations. The availability of such predictions can offer significant assistance to those who are working to reduce air pollution.     

BAF处理系统的BP神经网络模型

本文以某污水处理厂曝气生物滤池（Biologlcal aerated filter，BAF）的实际运行数据为基础，采用人工神经网络（Artificial neural network，ANN）方法，建立起BAF处理系统的BP神经网络预测模型。模型运算结果表明，预测值和实测值能较好地吻合，起到了模拟预测的效果，同时能优化运行状态。该模型的建立为BAF处理系统的预测及运行管理供了一条简便实用的途径，具有良好的研究和工程实用价值。     

Estimating tree bole volume using artificial neural network models for four species in Turkey

Tree bole volumes of 89 Scots pine (Pinus sylvestris L.), 96 Brutian pine (Pinus brutia Ten.), 107 Cilicica fir (Abies cilicica Carr.) and 67 Cedar of Lebanon (Cedrus libani A. Rich.) trees were estimated using Artificial Neural Network (ANN) models. Neural networks offer a number of advantages including the ability to implicitly detect complex nonlinear relationships between input and output variables, which is very helpful in tree volume modeling. Two different neural network architectures were used and produced the Back propagation (BPANN) and the Cascade Correlation (CCANN) Artificial Neural Network models. In addition, tree bole volume estimates were compared to other established tree bole volume estimation techniques including the centroid method, taper equations, and existing standard volume tables. An overview of the features of ANNs and traditional methods is presented and the advantages and limitations of each one of them are discussed. For validation purposes, actual volumes were determined by aggregating the volumes of measured short sections (average 1 meter) of the tree bole using Smalian's formula. The results reported in this research suggest that the selected cascade correlation artificial neural network (CCANN) models are reliable for estimating the tree bole volume of the four examined tree species since they gave unbiased results and were superior to almost all methods in terms of error (%) expressed as the mean of the percentage errors.     

Estimating monthly total nitrogen concentration in streams by using artificial neural network

Artificial Neural Network (ANN) is a flexible and popular tool for predicting the non-linear behavior in the environmental system. Here, the feed-forward ANN model was used to investigate the relationship among the land use, fertilizer, and hydrometerological conditions in 59 river basins over Japan and then applied to estimate the monthly river total nitrogen concentration (TNC). It was shown by the sensitivity analysis, that precipitation, temperature, river discharge, forest area and urban area have high relationships with TNC. The ANN structure having eight inputs and one hidden layer with seven nodes gives the best estimate of TNC. The 1:1 scatter plots of predicted versus measured TNC were closely aligned and provided coefficients of errors of 0.98 and 0.93 for ANNs calibration and validation, respectively. From the results obtained, the ANN model gave satisfactory predictions of stream TNC and appears to be a useful tool for prediction of TNC in Japanese streams. It indicates that the ANN model was able to provide accurate estimates of nitrogen concentration in streams. Its application to such environmental data will encourage further studies on prediction of stream TNC in ungauged rivers and provide a useful tool for water resource and environment managers to obtain a quick preliminary assessment of TNC variations.