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.     

Effects of land use change and water reuse options on urban water cycle

The aim of this article was to study the effects of land use change and water reuse options on an urban water cycle. A water cycle analysis was performed on the Goonja drainage basin, located in metropolitan Seoul, using the Aquacycle model. The chronological e ects of urbanization were first assessed for the land uses of the Goonja drainage basin from 1975 to 2005, where the ratio of impervious areas ranged from 43% to 84%. Progressive urbanization was identified as leading to a decrease in evapotranspiration (29%), an increase in surface runo (41%) and a decrease in groundwater recharge (74%), indicating a serious distortion of the water cycle. From a subsequent analysis of the water reuse options, such as rainwater use and wastewater reuse, it is concluded that wastewater reuse seemed to have an advantage over rainwater use for providing a consistent water supply throughout the year for a country like Korea, where the rainy season is concentrated during the summer monsoon.     

Estimation of methane emission potential using the Clean Development Mechanism (CDM) tool for municipal solid waste landfill in Mandalay,Myanmar

Journal of Material Cycles and Waste Management - Municipal solid waste (MSW) landfills are the third largest source of global methane emissions as biogas (11%). In developing countries, MSW...     

Relationship between road traffic noisescape and urban form in Hong Kong

This paper reports on a study which explored the possible relationship between road traffic noisescape and urban form in Hong Kong. A total of 212 residential complexes from 11 contrasting urban forms were sampled, and their noise levels assessed both at dwelling and neighbourhood scales by noise mapping. Its findings indicate that residential complexes with different urban forms have significantly different noisescape attributes. There is a strong correlation between the noise characteristics and morphological indicators at the dwelling scale. A less obstreperous noisescape is associated with urban forms with lower road and building densities, and with building arrangements which provide self-noise screening. These findings suggest that urban form is an influential determinant of the noisescape in the urban environment, and they point to the need to rethink the conventional approach to managing the urban acoustic environment.     

Early atmospheric detection of carbon dioxide from carbon capture and storage sites

The early atmospheric detection of carbon dioxide (CO₂) leaks from carbon capture and storage (CCS) sites is important both to inform remediation efforts and to build and maintain public support for CCS in mitigating greenhouse gas emissions. A gas analysis system was developed to assess the origin of plumes of air enriched in CO₂, as to whether CO₂ is from a CCS site or from the oxidation of carbon compounds. The system measured CO₂ and O₂ concentrations for different plume samples relative to background air and calculated the gas differential concentration ratio (GDCR = ?ΔO₂/ΔCO₂). The experimental results were in good agreement with theoretical calculations that placed GDCR values for a CO₂ leak at 0.21, compared with GDCR values of 1–1.8 for the combustion of carbon compounds. Although some combustion plume samples deviated in GDCR from theoretical, the very low GDCR values associated with plumes from CO₂ leaks provided confidence that this technology holds promise in providing a tool for the early detection of CO₂ leaks from CCS sites. Implications: This work contributes to the development of a cost-effective technology for the early detection of leaks from sites where CO₂ has been injected into the subsurface to enhance oil recovery or to permanently store the gas as a strategy for mitigating climate change. Such technology will be important in building public confidence regarding the safety and security of carbon capture and storage sites.     

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.