Applying life cycle assessment to analyze the environmental sustainability of public transit modes for the City of Toronto

One challenge related to transit planning is selecting the appropriate mode: bus, light rail transit (LRT), regional express rail (RER), or subway. This project uses data from life cycle assessment to develop a tool to measure energy requirements for different modes of transit, on a per passenger-kilometer basis. For each of the four transit modes listed, a range of energy requirements associated with different vehicle models and manufacturers was developed. The tool demonstrated that there are distinct ranges where specific transit modes are the best choice. Diesel buses are the clear best choice from 7-51 passengers, LRTs make the most sense from 201-427 passengers, and subways are the best choice above 918 passengers. There are a number of other passenger loading ranges where more than one transit mode makes sense; in particular, LRT and RER represent very energy-efficient options for ridership ranging from 200 to 900 passengers. The tool developed in the thesis was used to analyze the Bloor-Danforth subway line in Toronto using estimated ridership for weekday morning peak hours. It was found that ridership across the line is for the most part actually insufficient to justify subways over LRTs or RER. This suggests that extensions to the existing Bloor-Danforth line should consider LRT options, which could service the passenger loads at the ends of the line with far greater energy efficiency. It was also clear that additional destinations along the entire transit line are necessary to increase the per passenger-kilometer energy efficiency, as the current pattern of commuting to downtown leaves much of the system underutilized. It is hoped that the tool developed in this thesis can be used as an additional resource in the transit mode decision-making process for many developing transportation systems, including the transit systems across the GTHA.

A Generalized Fuzzy Linguistic Model for Predicting Component Concentrations in an Optical Gas Sensing System

Motivated by environmental protection concerns, monitoring the flue gas of thermal power plant is now often mandatory due to the need to ensure that emission levels stay within safe limits. Optical based gas sensing systems are increasingly employed for this purpose, with regression techniques used to relate gas optical absorption spectra to the concentrations of specific gas components of interest (NOx, SO2 etc.). Accurately predicting gas concentrations from absorption spectra remains a challenging problem due to the presence of nonlinearities in the relationships and the high-dimensional and correlated nature of the spectral data. This article proposes a generalized fuzzy linguistic model (GFLM) to address this challenge. The GFLM is made up of a series of “If-Then” fuzzy rules. The absorption spectra are input variables in the rule antecedent. The rule consequent is a general nonlinear polynomial function of the absorption spectra. Model parameters are estimated using least squares and gradient descent optimization algorithms. The performance of GFLM is compared with other traditional prediction models, such as partial least squares, support vector machines, multilayer perceptron neural networks and radial basis function networks, for two real flue gas spectral datasets: one from a coal-fired power plant and one from a gas-fired power plant. The experimental results show that the generalized fuzzy linguistic model has good predictive ability, and is competitive with alternative approaches, while having the added advantage of providing an interpretable model.

A generalized fuzzy linguistic model for predicting component concentrations in an optical gas sensing system

Motivated by environmental protection concerns, monitoring the flue gas of thermal power plant is now often mandatory due to the need to ensure that emission levels stay within safe limits. Optical based gas sensing systems are increasingly employed for this purpose, with regression techniques used to relate gas optical absorption spectra to the concentrations of specific gas components of interest (NO_x, SO₂ etc.). Accurately predicting gas concentrations from absorption spectra remains a challenging problem due to the presence of nonlinearities in the relationships and the high-dimensional and correlated nature of the spectral data. This article proposes a generalized fuzzy linguistic model (GFLM) to address this challenge. The GFLM is made up of a series of “If-Then” fuzzy rules. The absorption spectra are input variables in the rule antecedent. The rule consequent is a general nonlinear polynomial function of the absorption spectra. Model parameters are estimated using least squares and gradient descent optimization algorithms. The performance of GFLM is compared with other traditional prediction models, such as partial least squares, support vector machines, multilayer perceptron neural networks and radial basis function networks, for two real flue gas spectral datasets: one from a coal-fired power plant and one from a gas-fired power plant. The experimental results show that the generalized fuzzy linguistic model has good predictive ability, and is competitive with alternative approaches, while having the added advantage of providing an interpretable model.