Evolutionary algorithm for vehicle driving cycle generation

Modeling transit bus emissions and fuel economy requires a large amount of experimental data over wide ranges of operational conditions. Chassis dynamometer tests are typically performed using representative driving cycles defined based on vehicle instantaneous speed as sequences of "microtrips", which are intervals between consecutive vehicle stops. Overall significant parameters of the driving cycle, such as average speed, stops per mile, kinetic intensity, and others, are used as independent variables in the modeling process. Performing tests at all the necessary combinations of parameters is expensive and time consuming. In this paper, a methodology is proposed for building driving cycles at prescribed independent variable values using experimental data through the concatenation of "microtrips" isolated from a limited number of standard chassis dynamometer test cycles. The selection of the adequate "microtrips" is achieved through a customized evolutionary algorithm. The genetic representation uses microtrip definitions as genes. Specific mutation, crossover, and karyotype alteration operators have been defined. The Roulette-Wheel selection technique with elitist strategy drives the optimization process, which consists of minimizing the errors to desired overall cycle parameters. This utility is part of the Integrated Bus Information System developed at West Virginia University.     

Modeling transit bus fuel consumption on the basis of cycle properties

A method exists to predict heavy-duty vehicle fuel economy and emissions over an "unseen" cycle or during unseen on-road activity on the basis of fuel consumption and emissions data from measured chassis dynamometer test cycles and properties (statistical parameters) of those cycles. No regression is required for the method, which relies solely on the linear association of vehicle performance with cycle properties. This method has been advanced and examined using previously published heavy-duty truck data gathered using the West Virginia University heavy-duty chassis dynamometer with the trucks exercised over limited test cycles. In this study, data were available from a Washington Metropolitan Area Transit Authority emission testing program conducted in 2006. Chassis dynamometer data from two conventional diesel buses, two compressed natural gas buses, and one hybrid diesel bus were evaluated using an expanded driving cycle set of 16 or 17 different driving cycles. Cycle properties and vehicle fuel consumption measurements from three baseline cycles were selected to generate a linear model and then to predict unseen fuel consumption over the remaining 13 or 14 cycles. Average velocity, average positive acceleration, and number of stops per distance were found to be the desired cycle properties for use in the model. The methodology allowed for the prediction of fuel consumption with an average error of 8.5% from vehicles operating on a diverse set of chassis dynamometer cycles on the basis of relatively few experimental measurements. It was found that the data used for prediction should be acquired from a set that must include an idle cycle along with a relatively slow transient cycle and a relatively high speed cycle. The method was also applied to oxides of nitrogen prediction and was found to have less predictive capability than for fuel consumption with an average error of 20.4%.     

Further Validation of Artificial Neural Network-Based Emissions Simulation Models for Conventional and Hybrid Electric Vehicles

Abstract

With the advent of hybrid electric vehicles, computer-based vehicle simulation becomes more useful to the engineer and designer trying to optimize the complex combination of control strategy, power plant, drive train, vehicle, and driving conditions. With the desire to incorporate emissions as a design criterion, researchers at West Virginia University have developed artificial neural network (ANN) models for predicting emissions from heavy-duty vehicles. The ANN models were trained on engine and exhaust emissions data collected from transient dynamometer tests of heavy-duty diesel engines then used to predict emissions based on engine speed and torque data from simulated operation of a tractor truck and hybrid electric bus. Simulated vehicle operation was performed with the ADVISOR software package. Predicted emissions (carbon dioxide [CO₂] and oxides of nitrogen [NO_x]) were then compared with actual emissions data collected from chassis dynamometer tests of similar vehicles. This paper expands on previous research to include different driving cycles for the hybrid electric bus and varying weights of the conventional truck. Results showed that different hybrid control strategies had a significant effect on engine behavior (and, thus, emissions) and may affect emissions during different driving cycles. The ANN models underpredicted emissions of CO₂ and NO_x in the case of a class-8 truck but were more accurate as the truck weight increased.     

Analysis and modelling of the pollutant emissions from European cars regarding the driving characteristics and test cycles

Within the European research project ARTEMIS, significant works have been conducted to analyse the hot emissions of pollutant from the passenger cars regarding the driving cycles and to propose modelling approaches taking into account large but heterogeneous datasets recorded in Europe. The review and analysis of a large range of test cycles enabled first the building-up of a set of contrasted cycles specifically designed for characterizing the influence of the driving conditions. These cycles were used for the measurement of the pollutants emission rates from nine passenger cars on a chassis dynamometer.Emissions measured on 30 vehicles tested on cycles adapted to their motorization (i.e., cycles for high- or low-powered cars, inducing thus a significant difference in the dynamic) were also considered for analysing the influence of the cycles and of the kinematic parameters on the hot emission rates of the regulated pollutants (CO, HC, NO_x, CO₂, PM). An analyses of variance demonstrated the preponderance of the driving type (urban, rural road, motorway), of the vehicle category (fuel, emission standard) and emitting status (high/normal emitter) and thus the pertinence of analysing and modelling separately the corresponding emissions. It also demonstrated that Urban driving led systematically to high diesel emission rates and to high CO₂, HC and NO_x emissions from petrol cars. Congested driving implied high CO₂ (diesel and petrol) and high diesel NO_x emission. On motorway, the very high speeds generated high CO₂, while unsteady speeds induced diesel NO_x and petrol CO over-emissions. A search for pertinent kinematic parameters showed that urban diesel emissions were mostly sensitive to stops and speed parameters, while petrol emissions were rather sensitive to acceleration parameters. On the motorway, diesel NO_x and CO₂ emissions rates increased with the speed variability and occurrence of high speeds, while CO₂ and CO over-emission from petrol cars were linked to the occurrence of strong acceleration at high speeds.A modelling approach based on partial least square regression was tested, which demonstrates its ability to discriminate satisfactorily the emissions according to dynamic related parameters and in particular when considering the two-dimensionnal distribution of instantaneous speed and acceleration.Finally, a strategy was proposed to analyse the large but heterogeneous set of hot emission data collected within the ARTEMIS project. The approach consisted in analysing the similarity of the numerous cycles as regards their kinematic, grouping them into reference test patterns through an automatic clustering, and then computing reference emissions for these patterns. These principles enabled the development of a method to compute the emissions at a low spatial scale, i.e. the so-called traffic situation approach, which was implemented in the European Artemis model for estimating the cars’ pollutant emissions.     

A bottom-up clustering approach to identify bus driving patterns and to develop bus driving cycles for Hong Kong

Bus transport has been an important mode taking up a significant share of urban travel demand and thus the corresponding impacts on the environment are of great concerns. Use of driving cycles to evaluate the environmental impacts of buses has attracted much attention in recent years worldwide. The franchised bus service is currently playing important roles in the public transport system in Hong Kong; however, there is no driving cycle developed specifically for them. A set of bus driving cycle was therefore developed using a bottom-up approach where driving data on the bus network with mixed characteristics were collected. Using the Ward’s method for clustering, the collected data were then categorized into three clusters representing distinct franchised bus route patterns in Hong Kong. Driving cycles were then developed for each route pattern including (i) congested urban routes with closely spaced bus stops and traffic junctions; (ii) inter-district routes containing a number of stop-and-go activities and a significant portion of smoother high speed driving; and (iii) early morning express routes and mid-night routes connecting remote residential areas and urban areas. These cycles highlighted the unique low-speed and aggressive driving characteristics of bus transport in Hong Kong with frequent stop-and-go activities. The findings from this study would definitely be helpful in assessing the exhaust emissions, fuel consumptions as well as energy consumptions of bus transport. The bottom-up clustering approach adopted in this study would also be useful in identifying specific driving patterns based on vehicle speed trip data with mixed driving characteristics. It is believed that this approach is especially suitable for assessing fixed route public transport modes with mixed driving characteristics.

     

On-Road Motor Vehicle Emissions and Fuel Consumption in Urban Driving Conditions

ABSTRACT

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, NO_x, 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.     

Changing Speed-VMT Distributions: The Effects on Emissions Inventories and Conformity

ABSTRACT

The emissions factor modeling component of the motor vehicle emissions inventory (MVEI) modeling suite is currently being revised by the California Air Resources Board (CARB). One of the proposed changes in modeling philosophy is a shift from using link-based travel activity data to trip-based travel data for preparing mobile emissions inventories. Also as part of the revisions, new speed correction factors (SCFs) will be developed by CARB for the revised model. The new SCFs will be derived from vehicle emissions on 15 new driving cycles, each constructed to represent a typical trip at a specific average speed. This paper discusses how the new SCFs will affect transportation conformity and emissions inventory development, and evaluates the differences in total emissions produced by trip-based and link-based distributions of speed and vehicle miles of travel (VMT).

We simulated both link-based and trip-based speed-VMT distributions using travel data from the Sacramento and San Diego travel demand models. On the basis of the simulation results, there is reason to expect that mobile emissions inventories constructed using the proposed trip-based philosophy will differ markedly from those constructed in the current manner. Noting that results may vary by region, increases are expected in the CO and HC inventory levels, with concomitant decreases in the NO_x mobile emissions inventories.     

Effects of diesel/biodiesel blends on regulated and unregulated pollutants from a passenger vehicle operated over the European and the Athens driving cycles

This paper presents the regulated and unregulated exhaust emissions of a diesel passenger vehicle, operated with low sulphur automotive diesel and soy methyl ester blends. Emission and fuel consumption measurements were conducted under real driving conditions (Athens Driving Cycle, ADC) and compared with those of a modified New European Driving Cycle (NEDC) using a chassis dynamometer. A Euro II compliant diesel vehicle was used in this study, equipped with an indirect injection diesel engine, fuelled with diesel fuel and biodiesel blends at proportions of 5, 10, and 20% respectively. Unregulated emissions of 11 polycyclic aromatic hydrocarbons (PAHs), 5 nitro-PAHs, 13 carbonyl compounds (CBCs) and the soluble organic fraction (SOF) of the particulate matter were measured. Qualitative hydrocarbon analysis was also performed on the SOF. Regulated emissions of NO_x, CO, HC, CO₂, and PM were also measured over the two test cycles. It was established that some of the emissions measured over the (hot-start) NEDC differed from the real-world cycle. Significant differences were also observed in the vehicle's fuel consumption between the two test cycles. The addition of biodiesel reduced the regulated emissions of CO, HC and PM, while an increase in NO_x was observed over the ADC. Carbonyl emissions, PAHs and nitro-PAHs were reduced with the addition of biodiesel over both driving cycles.     

Characterization of Real-World Activity,Fuel Use,and Emissions for Selected Motor Graders Fueled with Petroleum Diesel and B20 Biodiesel

Abstract

Motor graders are a common type of nonroad vehicle used in many road construction and maintenance applications. In-use activity, fuel use, and emissions were measured for six selected motor graders using a portable emission measurement system. Each motor grader was tested with petroleum diesel and B20 biodiesel. Duty cycles were quantified in terms of the empirical cumulative distribution function of manifold absolute pressure (MAP), which is an indicator of engine load. The motor graders were operated under normal duty cycles for road maintenance and repair at various locations in Wake and Nash Counties in North Carolina. Approximately 3 hr of quality-assured, second-by-second data were obtained during each test. An empirical modal-based model of vehicle fuel use and emissions was developed, based on stratifying the data with respect to ranges of normalized MAP, to enable comparisons between duty cycles, motor graders, and fuels. Time-based emission factors were found to increase monotonically with MAP. Fuel-based emission factors were mainly sensitive to differences between idle and non-idle engine operation. Cycle average emission factors were estimated for road “resurfacing”, “roading,” and “shouldering” activities. On average, the use of B20 instead of petroleum diesel leads to a negligible decrease of 1.6% in nitric oxide emission rate, and decreases of 19– 22% in emission rates of carbon monoxide, hydrocarbons, and particulate matter. Emission rates decrease significantly when comparing newer engine tier vehicles to older ones. Significant reductions in tailpipe emissions accrue especially from the use of B20 and adoption of newer vehicles.     

An exploratory analysis comparing a stochastic driving cycle to California's regulatory cycle

As the fundamental building block of the emissions estimation process, a driving cycle needs to be representative of real-world driving behavior. The driving cycle construction method becomes crucial for generating a representative driving cycle. In this paper, we revisit the Unified Cycle's (i.e., the LA92 driving cycle) construction method. The California Air Resources Board's Unified Cycle used a “microtrips” approach, a speed–acceleration frequency distribution plot, and a quasi-random selection mechanism to build the driving cycle. There is concern that the Unified Cycle does not reflect the true driving patterns due to the identified flaws in the construction methodology. Treating a driving trace as a stochastic process, we construct a new driving cycle (LA01) with the same driving data originally used to build the Unified Cycle. We then compare the two driving cycles with the sample data set with respect to the durations and intensities of the modal events. The new driving cycle is found to better replicate the modal events observed in the sample data. A comparison of average road power values between the sample data, LA01, and the Unified Cycle also confirms the effect of fine-scale driving on emissions. These differences result from the different construction approaches and can be expected to affect emissions inventory estimation.     

VOC composition and ozone-forming potential of the exhaust gas of in-use motorcycles

The emission profile of volatile organic compounds (VOC) and the ozone-forming potential (OP) of the exhaust gas of six in-use motorcycles (four 4-stroke- and two 2-stroke-engines) were determined. The motorcycles were tested on a chassis dynamometer in a real-world driving cycle. The analysis involved the C2–C12-hydrocarbons as well as the aldehydes and ketones. Additionally, the regulated THC and NO_x emissions were measured according to the test procedure for type approval (ECE 40). Two vehicles did not fulfil the THC emission standard, whereas all vehicles met the requirements for NO_x emission. The aromatic fuel components toluene and xylene, and the combustion products ethene and propene contributed most to the OP of the VOC emission. The highest OP was found with the 2-stroke engines. The VOC profile of the emissions varied with vehicle and driving conditions. The reactivity of the exhaust gas, defined as gram ozone per gram of non-methane organic gases (NMOG), increased with vehicle speed.     

Effects of Fuel Type,Driving Cycle,and Emission Status on In-Use Vehicle Exhaust Reactivity

ABSTRACT

The introduction of reformulated gasolines significantly reduced exhaust hydrocarbon (HC) mass emissions, but few data are available concerning how these new fuels affect exhaust reactivity. Similarly, while it is well established that high-emitting vehicles contribute a significant portion of total mobile source HC mass emissions, it is also important to evaluate the exhaust reactivity from these vehicles. The objective of this study was to evaluate the relative influence on in-use vehicle exhaust reactivity of three critical factors: fuel, driving cycle, and vehicle emission status. Nineteen in-use vehicles were tested with seven randomly assigned fuel types and two driving cycles: the Federal Test Procedure (FTP) and the Unified Cycle (UC). Total exhaust reactivity was not statistically different between the FTP and UC cycles but was significantly affected by fuel type. On average, the exhaust reactivity for California Phase 2 fuel was the lowest (16 % below the highest fuel type) among the seven fuels tested for cold start emissions. The average exhaust reactivity for high-emitting vehicles was significantly higher for hot stabilized (11%) and hot start (15%) emissions than for low-emitting vehicles. The exhaust reactivities for the FTP and UC cycles for light-end HCs and carbonyls were significantly different for the hot stabilized mode. There was a significant fuel effect on the mean specific reactivity (SR) for the mid-range HCs, but not for light-end HCs or carbonyls, while vehicle emission status affected the mean SR for all three HC compound classes.     

A Chassis Test Procedure to Mimic the Heavy-Duty Engine Transient Emissions Certification Test

ABSTRACT

In-use emissions from vehicles using heavy-duty diesel engines can be significantly higher than the levels obtained during engine certification. These higher levels may be caused by a combination of degradation of engine components, poor engine maintenance, degradation or failure of emissions after-treatment devices, and engine and emissions system tampering. A direct comparison of in-use vehicle emissions with engine certification levels, however, is not possible without removing an engine from the vehicle in order to perform engine dynamometer emissions testing. The goal of this research was to develop a chassis test procedure that mimics the engine performance, and as such the expected emissions levels, from the engine certification emissions test prescribed in the U.S. Code of Federal Regulations. Emissions measurements were taken from two engines during testing on an engine dynamometer using the transient heavy-duty Federal Test Procedure (FTP). Additionally, each engine was installed in an appropriate vehicle, and emissions measurements were taken using a chassis dynamometer while employing a vehicle driving schedule     

Developing a high-resolution vehicular emission inventory by integrating an emission model and a traffic model: Part 1--Modeling fuel consumption and emissions based on speed and vehicle-specific power

To improve the accuracy and applicability of vehicular emission models, this study proposes a speed and vehicle-specific power (VSP) modeling method to estimate vehicular emissions and fuel consumption using data gathered by a portable emissions monitoring system (PEMS). The PEMS data were categorized into discrete speed-VSP bins on the basis of the characteristics of vehicle driving conditions and emissions in Chinese cities. Speed-VSP modal average rates of emissions (or fuel consumption) and the time spent in the corresponding speed-VSP bins were then used to calculate the total trip emissions (or fuel consumption) and emission factors (or fuel economy) under specific average link speeds. The model approach was validated by comparing it against measured data with prediction errors within 20% for trip emissions and link-speed-based emission factors. This analysis is based on the data of light-duty gasoline vehicles in China; however, this research approach could be generalized to other vehicle fleets in other countries. This modeling method could also be coupled with traffic demand models to establish high-resolution emissions inventories and evaluate the impacts of traffic-related emission control measures.     

Tomato Root: Site of Initial Alteration in Minor Elements in Cadmium Treated Plants

Abstract

Societal and governmental pressures to reduce diesel exhaust emissions are reflected in the existing and projected future heavy-duty certification standards of these emissions. Various factors affect the amount of emissions produced by a heterogeneous charge diesel engine in any given situation, but these are poorly quantified in the existing literature. The parameters that most heavily affect the emissions from compression ignition engine-powered vehicles include vehicle class and weight, driving cycle, vehicle vocation, fuel type, engine exhaust aftertreatment, vehicle age, and the terrain traveled. In addition, engine control effects (such as injection timing strategies) on measured emissions can be significant. Knowing the effect of each aspect of engine and vehicle operation on the emissions from diesel engines is useful in determining methods for reducing these emissions and in assessing the need for improvement in inventory models. The effects of each of these aspects have been quantified in this paper to provide an estimate of the impact each one has on the emissions of diesel engines.     

Criteria and Air-Toxic Emissions from In-Use Automobiles in the National Low-Emission Vehicle Program

Abstract

The U.S. Environmental Protection Agency (EPA) implemented a program to identify tailpipe emissions of criteria and air-toxic contaminants from in-use, light-duty low-emission vehicles (LEVs). EPA recruited 25 LEVs in 2002 and measured emissions on a chassis dynamometer using the cold-start urban dynamometer driving schedule of the Federal Test Procedure. The emissions measured included regulated pollutants, particulate matter, speciated hydrocarbon compounds, and carbonyl compounds. The results provided a comparison of emissions from real-world LEVs with emission standards for criteria and air-toxic compounds. Emission measurements indicated that a portion of the in-use fleet tested exceeded standards for the criteria gases. Real-time regulated and speciated hydrocarbon measurements demonstrated that the majority of emissions occurred during the initial phases of the cold-start portion of the urban dynamometer driving schedule. Overall, the study provided updated emission factor data for real-world, in-use operation of LEVs for improved emissions modeling and mobile source inventory development.     

A Modal Approach to Vehicular Emissions and Fuel Consumption Model Development

Abstract

This study reports on the analysis of emissions and fuel consumption from motor vehicles using a modal approach. The four standard driving modes are idling, accelerating, cruising, and decelerating. On‐road data were collected using instrumented test vehicles traveling many times through the urban areas of Hong Kong. A model was developed for estimating vehicular fuel consumption and emissions as a function of instantaneous speed and driving mode. Piecewise interpolation functions were proposed for each nonidling driving mode. Idling emission and fuel consumption rates were estimated as negative exponential functions of idling time. Preliminary modeling results showed good agreements for the test vehicles and indicated that the on‐road measurements are feasible for the development of modal emission and fuel consumption models.     

Real-world fuel use and gaseous emission rates for flex fuel vehicles operated on E85 versus gasoline

Flex fuel vehicles (FFVs) typically operate on gasoline or E85, an 85%/15% volume blend of ethanol and gasoline. Differences in FFV fuel use and tailpipe emission rates are quantified for E85 versus gasoline based on real-world measurements of five FFVs with a portable emissions measurement system (PEMS), supplemented chassis dynamometer data, and estimates from the Motor Vehicle Emission Simulator (MOVES) model. Because of inter-vehicle variability, an individual FFV may have higher nitrogen oxide (NO_x) or carbon monoxide (CO) emission rates on E85 versus gasoline, even though average rates are lower. Based on PEMS data, the comparison of tailpipe emission rates for E85 versus gasoline is sensitive to vehicle-specific power (VSP). For example, although CO emission rates are lower for all VSP modes, they are proportionally lowest at higher VSP. Driving cycles with high power demand are more advantageous with respect to CO emissions, but less advantageous for NO_x. Chassis dynamometer data are available for 121 FFVs at 50,000 useful life miles. Based on the dynamometer data, the average difference in tailpipe emissions for E85 versus gasoline is ?23% for NO_x, ?30% for CO, and no significant difference for hydrocarbons (HC). To account for both the fuel cycle and tailpipe emissions from the vehicle, a life cycle inventory was conducted. Although tailpipe NO_x emissions are lower for E85 versus gasoline for FFVs and thus benefit areas where the vehicles operate, the life cycle NO_x emissions are higher because the NO_x emissions generated during fuel production are higher. The fuel production emissions take place typically in rural areas. Although there are not significant differences in the total HC emissions, there are differences in HC speciation. The net effect of lower tailpipe NO_x emissions and differences in HC speciation on ozone formation should be further evaluated.

Implications: Reported comparisons of flex fuel vehicle (FFV) tailpipe emission rates for E85 versus gasoline have been inconsistent. To date, this is the most comprehensive evaluation of available and new data. The large range of inter-vehicle variability illustrates why prior studies based on small sample sizes led to apparently contradictory findings. E85 leads to significant reductions in tailpipe nitrogen oxide (NO_x) and carbon monoxide (CO) emission rates compared with gasoline, indicating a potential benefit for ozone air quality management in NO_x-limited areas. The comparison of FFV tailpipe emissions between E85 and gasoline is sensitive to power demand and driving cycles.     

Emission Factors for Gasoline Light-Duty Vehicles: Experimental Program in Santiago,Chile

ABSTRACT

The emission inventory of the city of Santiago, Chile, related to mobile sources was built up using constant emission factors extracted from international literature. To improve the estimate of mobile source emissions, an experimental program was designed, consisting of transient tests on a chassis dynamometer over a sample of about 166 vehicles, applying 9 local driving cycles with average speeds of 3-80 km/hr, and experimentally determined in previous research carried out by the authors. An analysis of the influence of fuel inlet technology, and a year time-length model over emissions, was undertaken. We proposed emission factors as a function of average speed and of CO, THC, and NO_x for catalytic and noncatalytic light-duty gasoline vehicles, disaggregated on commercial and private cars. A comparative analysis with emission factors obtained for the application of the COPERT II and AP-42 models was also presented. Our current analysis gives solid evidence indicating that to obtain a reasonable accuracy on emission estimates and calculations, local emission factors must be used.     

Further validation of artificial neural network-based emissions simulation models for conventional and hybrid electric vehicles

With the advent of hybrid electric vehicles, computer-based vehicle simulation becomes more useful to the engineer and designer trying to optimize the complex combination of control strategy, power plant, drive train, vehicle, and driving conditions. With the desire to incorporate emissions as a design criterion, researchers at West Virginia University have developed artificial neural network (ANN) models for predicting emissions from heavy-duty vehicles. The ANN models were trained on engine and exhaust emissions data collected from transient dynamometer tests of heavy-duty diesel engines then used to predict emissions based on engine speed and torque data from simulated operation of a tractor truck and hybrid electric bus. Simulated vehicle operation was performed with the ADVISOR software package. Predicted emissions (carbon dioxide [CO2] and oxides of nitrogen [NO(x)]) were then compared with actual emissions data collected from chassis dynamometer tests of similar vehicles. This paper expands on previous research to include different driving cycles for the hybrid electric bus and varying weights of the conventional truck. Results showed that different hybrid control strategies had a significant effect on engine behavior (and, thus, emissions) and may affect emissions during different driving cycles. The ANN models underpredicted emissions of CO2 and NO(x) in the case of a class-8 truck but were more accurate as the truck weight increased.