BP neural network classification on passenger vehicle type based on GA of feature selection

This paper has concluded six features that belong to passenger vehicle types based on genetic algorithm(GA)of feature selection.We have obtained an optimal feature subset,including length,ratio of width and length,and ratio of height and length.And then we apply this optimal feature subset as well as another feature set,containing length,width and height,to the network input.Back-propagation(BP)neural network and support vector machine(SVM)are applied to classify the passenger vehicle type.There are four passenger vehicle types.This paper selects 400 samples of passenger vehicles,among which 320 samples are used as training set(each class has 80 samples)and the other 80 samples as testing set,taking the feature of the samples as network input and taking four passenger vehicle types as output.For the test,we have applied BP neural network to choose the optimal feature subset as network input,and the results show that the total classification accuracy rate can reach 96%,and the classification accuracy rate of first type can reach 100%.In this condition,we obtain a conclusion that this algorithm is better than the traditional ones[9].

Influences of accumulated mileage and technological changes on emissions of regulated pollutants from gasoline passenger vehicles

In this study, the influences of accumulated mileage （deterioration） and technological changes （emission standards） on emission factors （EFs） of regulated pollutants （CO, HC, and NOx） from gasoline passenger vehicles were investigated based on Inspection and Maintenance （I/M） data using the chassis dynamometer method. The accumulated mileage of passenger vehicles was significantly linearly correlated with vehicle age. For most cases, the average EFs of CO, HC and NOx were significantly linearly correlated with accumulated mileage, indicating that emission deterioration had a significant impact on pollutant EFs. Implemented emission standards markedly influenced the EFs of regulated pollutants, and EFs markedly decreased with progressing emission standards. The present study also compared EFs of regulated pollutants between this study and the International vehicle emission （IVE） model, and marked differences in EFs were seen with variations in emission standards, vehicle types and accumulated mileage; NOx EFs in this study were higher than in the IVE model. The results provide new insight into estimating regulated pollutant emissions using the IVE model.

Implementation of a flexible Major Vacation Toll-free Program for small passenger vehicles in China

On July 24,2012,the State Council of the People’s Republic of China implemented'a toll-free program for small passenger vehicles during major vacations1).In the several months that followed,local governments issued implementation articles.The current Major Vacation Tollfree Program for small passenger vehicles(MVTP)pioneers the concept(Xu and Gao,2016),'Benefaction to People.'The current MVTP has received

Passenger Vehicle Registrations Rallied in February——registrations reflect auto market tendency

Passenger vehicles (including vans) registrations year-on-year increased 42.2% in Feb. 2007, reaching 408,570 units. Due to the reason there was a larger sales period before the past Chinese New Year in late of February, thus Feb. 2007 made a rather different tendency than previous years. The registrations exceeded more than 0.2 million compared with the

Who are on the road? A study on vehicle usage characteristics based on one-week vehicle trajectory data

Understanding the characteristics of passenger vehicle use is the prerequisite for effective urban management.However,it has been challenging in the existing literature due to the lack of continuously observed data on passenger vehicle use.Thanks to the advances in data collection and processing techniques,multi-day vehicle trajectory data generated from volunteered passenger cars provide new opportunities for examining in depth how people travel in regular patterns.In this paper,based on a week’s operation data of 6600 passenger cars in Shanghai,we develop a systematic approach for identifying trips and travel purposes,and classify vehicles into four categories using a Gaussian-Mixed-Model.A new method is proposed to identify vehicle travel regularities and we use the Z Test to explore differences in travel time and route choices between four types of vehicles.Wefind that commercially used vehicles present high travel intensity in temporal and spatial aspects and the use intensity in elevated roads is higher for household-used commuting vehicles than semi-commercially used vehicles.The methodologies and conclusions of this paper may provide not only theoretical support for future urban traffic prediction,but also guidance for employing customized active traffic demand management measures to alleviate traffic congestion.

A research into the application of the production capacity of passenger and light commercial vehicles in China

1. An overall judgment on the situation 2006 saw the rapid growth of passenger vehicles, with the production capacity putting into use rose from less than 70 percent to around 80 percent. That with light commercial vehicles was similar too. The situation in 2005 and 2006 showed that there are no evidential overdone production capacity.

Development of a Mobile Sensing Unit and Its Prototype Implementation

This paper represents a design and development of a mobile sensing unit as well as its prototype implementation for railway track monitoring. The unit consists of an ultra-small personal computer (PC), a global positioning system (GPS) receiver, an accelerometer and an ADC (Analog/Digital Converter) so that the unit can trace the route while capturing an acceleration response of a passenger vehicle. The unit enables more frequent and qualitative data acquisition compared with traditional and the state of the practice railway track inspection equipments. Locating disorder is the key of our unit, which has a reasonable accuracy of positioning with GPS data, existing facilities landmarks, and car acceleration responses. The proposed unit is a promising device for efficient properties management of railway agencies. The prototype implementation shows a result that car acceleration responses are related with the track displacements in low frequencies. The results also imply that sensor settlement on a vehicle floor, not axes or bogies, is effective for capturing track vertical displacements.

A four-dimensional interaction-based appraisal approach towards the performance enhancement of a vehicular waste heat recovery system

The non-linear multifactorial impacts on fuel-saving potential constrain the practical performance of the vehicular waste heat recovery system(WHRS). This study proposed a four-dimensional interaction-based appraisal approach to interpreting these impacts for enhancing WHRS's in-vehicle performance. The interaction incorporates a heat exchanger, configuration, engine,and vehicle. The proposed approach comprises two successive steps, emphasizing evaluation under the rated(Step 1) and off-design(Step 2) heat source conditions. A case study of waste heat recovery from a passenger vehicle was conducted to evaluate the in-vehicle performance of a novel co-split system and two single-split ones(with/without a regenerator) through this approach. The novel system theoretically modifies vehicular performance but remains ambiguous concerning real-world behaviour, which is assessed and verified by the proposed approach. Two key factors determining vehicular performance were identified by Step 1, namely, net power output and engine backpressure. As the co-split system modified both factors, its fuel-saving potential could be increased by up to 20.3% compared with single-split systems. Also, the limiting factor for off-design performance was pinpointed by Step 2, namely, the mismatch between the heat source and working fluid, which led to the solution, i.e., the synergistic split regulation of the working fluid and heat source. An up to 8.8% improvement in net power output was achieved by the co-split system at off-design heat sources compared with fixed split ratios. Consequently, the approach enables holistic performance improvement of the vehicular WHRS under design/off-design heat source conditions.

Replacing urban trucks via ground-air cooperation

The advent of drones is leading to a paradigm shift in courier services,while their large-scale deployment is confined by a limited range.Here,we design a low-cost product that allows drones to drop parcels onto and pick them up from the roofs of moving passenger vehicles.With this,we propose a ground-air cooperation(GAC)based business model for parcel delivery in an urban environment.As per our case study using real-world data in Beijing,the new business model will not only shorten the parcel delivery time by 86.5% with a comparable cost,but also reduce road traffic by 8.6%,leading to an annual social benefit of 6.67 billion USD for Beijing.The proposed model utilizes the currently“wasted or unused”rooftops of passenger vehicles and has the potential to replace most parcel trucks and trailers,thus fundamentally addressing the congestion,noise,pollution,and road wear and tear problems caused by trucks,and bringing in immense social benefit.