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.     

Potential application of high pressure carbon dioxide in treated wastewater and water disinfection: Recent overview and further trends

Recently emerging disadvantages in conventional disinfection have heightened the need for finding a new solution. Developments in the use of high pressure carbon dioxide for food preservation and sterilization have led to a renewed interest in its applicability in wastewater treatment and water disinfection. Pressurized CO₂ is one of the most investigated methods of antibacterial treatment and has been used extensively for decades to inhibit pathogens in dried food and liquid products. This study reviews the literature concerning the utility of CO₂ as a disinfecting agent, and the pathogen inactivation mechanism of CO₂ treatment is evaluated based on all available research. In this paper, it will be argued that the successful application and high effectiveness of CO₂ treatment in liquid foods open a potential opportunity for its use in wastewater treatment and water disinfection. The findings from models with different operating conditions (pressure, temperature, microorganism, water content, media …) suggest that most microorganisms are successfully inhibited under CO₂ treatment. It will also be shown that the bacterial deaths under CO₂ treatment can be explained by many different mechanisms. Moreover, the findings in this study can help to address the recently emerging problems in water disinfection, such as disinfection by-products (resulting from chlorination or ozone treatment).     

Toxicity of carbaryl,diquat dibromide,and fluoranthene,individually and in mixture,to larval grass shrimp,Palaemonetes pugio

This study examined the toxicity of two pesticides (carbaryl and diquat dibromide) and one polycyclic aromatic hydrocarbon (fluoranthene), both singly and in mixture, to grass shrimp larvae (Palaemonetes pugio). These three chemicals are all present in coastal environments and can easily enter estuarine ecosystems. Fluoranthene was the most toxic chemical with a 96-h LC₅₀ value of 32.45 μ g/L, followed by carbaryl (43.02 μ g/L) and diquat dibromide (1624 μ g/L). In the chemical mixture tests, the binary carbaryl/diquat dibromide mixture and the ternary carbaryl/diquat dibromide/fluoranthene mixture had additive results.     

Soot Control During the Combustion of Polystyrene

This paper describes an experimental study on the control of soot formation during the combustion of polystyrene (PS). A stable, twodimensional flame generated by using a Wolfhard-Parker type diffusion flame burner was used to simulate practical combustion situations. The combustion characteristics, effects of operating conditions on soot formation, and the effectiveness of various metallic additives as soot suppressants were investigated. It was found that soot yield could not be significantly reduced by controlling the oxidizer (air) flow rate. Increasing the O₂ mole fraction of the oxidlzer increased soot yield under typical operating conditions. However, soot yield could be greatly reduced by adding small amounts of air into the pyrolysis zone of the flame. The additional air would probably increase the combustion reaction rate while decreasing the soot precursor formation rate, thereby causing the observed effect. It was thus suggested that effective soot control could be accomplished by improving mixing between air and the PS devolatilizatlon products In practical combustion situations. The metallic additives tested in this study were the salts of Na, K, Ca, and Ba. Among these salts, Ca was the least effective in reducing soot, and K and Na were nearly equally effective. Ba was much more effective than all the others, and Its effectiveness was strongly dependent on its addition rate.     

A Value Orientation for Nature Preservation in Singapore

Over the past decade, the cause of nature preservation in Singapore had gained momentum through the efforts of the various non-governmental organisations. Tussles over disputed nature areas such as the Lower Peirce Forest, Marina South, Senoko, etc., had also garnered a great deal of publicity in the mass media. Many arguments for nature conservation were given by conservationists --- from the economic to the ecological --- without considering carefully their local relevance and impact. This paper provides an outline of a value orientation for nature preservation in Singapore --- taking into account the local context in terms of the economic, cultural, social and ecological conditions existing in this country. The major values usually associated with nature conservation are reviewed and prioritised in terms of local relevance and impact. The strategic thrust of the value orientation advocated is, in the final analysis, anthropocentric rather than non--anthropocentric in perspective.     

Performance of the hybrid growth sequencing batch reactor (HG-SBR) for biodegradation of phenol under various toxicity conditions

Hybrid growth microorganisms in sequencing batch reactors have proven effective for treating the toxic compound phenol, but the toxicity effect under different toxicity conditions has rarely been discussed. Therefore, the performance of the HG-SBR under toxic, acute and chronic organic loading can provide the overall operating conditions of the system. Toxic organic loading(TOL) was monitored during the first 7 hr while introducing50 mg/L phenol to the system. The system was adversely affected with the sudden introduction of phenol to the virgin activated sludge, which caused a low degradation rate and high dissolved oxygen consumption during TOL. Acute organic loading(AOL) had significant effects at high phenol concentrations(600, 800 1000 mg/L). The specific oxygen uptake rate(SOUR) gradually decreased to 4.9 mg O_2/(g MLVSS·hr) at 1000 mg/L of phenol compared to 12.74 mg O_2/(g MLVSS·hr) for 200 mg/L of phenol. The HG-SBR was further monitored during chronic organic loading(COL) over 67 days. The effects of organic loading were more apparent at 800 mg/L and 1000 mg/L phenol concentrations, as the removal range was between 22%–30% and 18%–46% respectively, which indicated the severe effects of COL.