Drive cycle recognition
Encyclopedia
Drive Cycle Recognition (abbr. DCR) is an advanced vehicle control strategy that uses past driving information, as well as a library of representative drive cycles
to extrapolate future vehicle control parameters. For example, the vehicle computer can identify past driving history as one particular representative cycle (say, FTP-75
) and use known information from FTP-75 to improve vehicle performance. This type of control strategy is most useful for hybrid vehicles where the control strategy has a much greater affect on vehicle performance than with a regular internal combustion engine driven vehicle.
Identification techniques can be as simple as numerical error calculations (such as Mean squared error
) or as complex as a self-organizing competitive neural network
.
Driving cycle
A driving cycle is a series of data points representing the speed of a vehicle versus time.Driving cycles are produced by different countries and organizations to assess the performance of vehicles in various ways, as for example fuel consumption and polluting emissions.Fuel consumption and...
to extrapolate future vehicle control parameters. For example, the vehicle computer can identify past driving history as one particular representative cycle (say, FTP-75
FTP-75
On October 22, 1996, the final rule on Motor Vehicle Emissions Federal Test Procedure Revisions was published in the United States Federal Register. This rule revises the tailpipe emissions portion of the Federal Test Procedure for Light-duty vehicles and light-duty trucks .FTP is shown in...
) and use known information from FTP-75 to improve vehicle performance. This type of control strategy is most useful for hybrid vehicles where the control strategy has a much greater affect on vehicle performance than with a regular internal combustion engine driven vehicle.
Identification techniques can be as simple as numerical error calculations (such as Mean squared error
Mean squared error
In statistics, the mean squared error of an estimator is one of many ways to quantify the difference between values implied by a kernel density estimator and the true values of the quantity being estimated. MSE is a risk function, corresponding to the expected value of the squared error loss or...
) or as complex as a self-organizing competitive neural network
Artificial neural network
An artificial neural network , usually called neural network , is a mathematical model or computational model that is inspired by the structure and/or functional aspects of biological neural networks. A neural network consists of an interconnected group of artificial neurons, and it processes...
.