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.     

Risk assessment of heavy metal contamination in shrimp farming in Mai Po Nature Reserve, Hong Kong

An ecological survey was carried out to determine the sediment concentrations of nutrients and heavy metals and bioaccumulation of heavy metals in fish and shrimp including tilapia (Oreochromis mossambicus×O. nilotica), grey mullet (Mugil cephalus), gei wai shrimp (Metapenaeus ensis) and caridean shrimp (Macrobrachium nipponensis) in the traditional tidal shrimp ponds (gei wais) of Mai Po Nature Reserve, Hong Kong. The sediments collected from the landward sites contained higher nutrient contents, as well as zinc (Zn), chromium (Cr), copper (Cu), nickel (Ni) and cadmium (Cd) than those collected from the seaward sites, but vice versa for lead (Pb) and mercury (Hg). However, the concentrations of all metals were exceptionally high in the two sites located outside the reserve, suggesting that waters from Deep Bay might be the possible source of metal contamination affecting the reserve. All metals studied seemed to accumulate in the viscera of fish. Body size was the determining factor for the accumulation of heavy metals in caridean shrimp and gei wai shrimp but not fish. Concentrations of the metals studied in tissues of grey mullet and gei wai shrimp were found to be safe for human consumption. Concentrations of Cr in tilapia whole body (0.68–1.10 mg kg⁻¹ wet weight) were close to or over the guideline value of 1 mg kg⁻¹ set by the Food Adulteration (Metallic Contamination) Regulations of Hong Kong. Tilapia flesh and small caridean shrimp collected from gei wais were contaminated by Cr and Pb but still fit for human consumption. Caution is required if large caridean shrimp is to be consumed in large amounts continuously because the concentration of Pb exceeded the maximum permitted concentration (6 mg kg⁻¹). The rather high Cr concentrations in tilapia whole body should not be overlooked as the fish will serve as a food source for migratory birds visiting the site.     

Physiological and behavioural responses of the intertidal scavenging gastropod Nassarius festivus to salinity changes

Physiology (oxygen consumption and ammonia excretion) and behaviour (feeding and activity) of the intertidal gastropod Nassarius festivus (Powys) at five different salinities [15, 20, 25 (control), 30 and 35‰] were studied for 4 weeks. Oxygen consumption and ammonia excretion rates were reduced immediately after salinity was either elevated or reduced. Subsequently, both rates were increased while the O:N ratio was decreased at all salinities, including the control, in the first 2 weeks and then levelled off. Such changes were probably attributed to osmotic adjustment and reproductive activity. Activity and feeding were reduced at low salinity, particularly in the first week. Reproductive output, in terms of the total number of egg capsules and the mean number of eggs per capsule, was also lowered at reduced salinities. Nevertheless, individuals at all salinities are able to maintain a positive energy balance. Results are discussed with respect to the distribution of N. festivus in Hong Kong waters. Received: 14 April 1997 / Accepted: 9 May 1997     

First trimester chorionic villus sampling versus mid-trimester genetic amniocentesis-preliminary results of a controlled prospective trial

This controlled prospective study assesses the relative risks of first trimester chorionic villus sampling (CVS) versus mid-trimester gentic amniocentesis (GA). CVS subjects and amnio-centesis controls were comparable with regard to several confounding variables which might influence the risk of pregnancy loss including maternal age, smoking, alcohol consumption, gestational age at study entry, and history of vaginal bleeding or poor prior reproductive outcome. The most common indication for prenatal diagnosis was advanced maternal age (n = 511). In this subgroup, spontaneous abortion (<24 weeks) occurred in 2·9 per cent of CVS subjects versus 4−3 per cent of amniocentesis controls. The sum of spontaneous and therapeutic abortions (<24 weeks) was identical (5·3 per cent) in both groups. Therefore, intervention in the CVS group (i.e., therapeutic abortion for cytogenetic abnormalities) did not influence the observed risk of pregnancy loss. Overall perinatal mortality rates were also similar in both groups. No significant differences were identified for a number of pregnancy outcome parameters including 5 min Apgar score, birth weight, body length, head circumference, gestational age at delivery, preterm delivery, fetal growth retardation, congenital malformations, and neonatal complications. Preliminary results of this controlled prospective study suggest that chorionic villus sampling carries a low and acceptable risk.     

Experimental and numerical study of the dispersion of motor vehicle pollutants under idle condition

The aim of the work presented here is to study experimentally and numerically the dispersion characteristics of vehicular exhaust plume at an idle condition in an idealized and simplified environment. The gaseous and particulate concentrations in the exhaust plume of three idling motor vehicles were measured in an isolated environment under calm weather conditions. Despite the difference in the initial concentrations, the pollutants decayed exponentially in all directions.The CFD code PHOENICS 3.3, with the k–ε eddy dissipation sub-model, was used for the numerical simulation. The simulated results match very well with the experimental results close to the source of emission but decay to the ambient concentrations much slower. The effects of the initial emission concentration, exit velocity, exit direction and crosswind intensity have been investigated parametrically. The initial pollutant concentration will increase the local concentrations but the pattern of dispersion remains the same. The exit velocity will increase the momentum of the jet, resulting in a deeper penetration downstream. The exit angle has a stronger influence on pollutant dispersion than both initial pollutant concentration and exit velocity. When the exit angle is 15°, the pollutants tend to spread on the ground region. Crosswind shows a significant effect on the dispersion of the exhaust plume also. It will divert the plume to disperse in the same direction of the wind with limited penetration in the downstream direction.     

On-road motor vehicle emissions and fuel consumption in urban driving conditions

This paper reports on the analysis of on-road vehicle speed, emission, and fuel consumption data collected by four instrumented vehicles. Time-, distance-, and fuel-based average fuel consumption, as well as CO, HC, NOx, and soot emission factors, were derived. The influences of instantaneous vehicle speed on emissions and fuel consumption were studied. It was found that the fuel-based emission factors varied much less than the time- and distance-based emission factors as instantaneous speed changed. The trends are similar to the results obtained from laboratory tests. The low driving speed contributed to a significant portion of the total emissions over a trip. Furthermore, the on-road data were analyzed using the modal approach. The four standard driving modes are acceleration, cruising, deceleration, and idling. It was found that the transient driving modes (i.e., acceleration and deceleration) were more polluting than the steady-speed driving modes (i.e., cruising and idling) in terms of g/km and g/sec. These results indicated that the on-road emission measurement is feasible in deriving vehicle emissions and fuel consumption factors in urban driving conditions.