US 11,815,875 B2
Methods, systems, and apparatuses of purge content estimation logic for improved fuel control
Jianyang Geng, South Lyon, MI (US); Scott R. Jeffrey, Hartland, MI (US); Steven W. Majors, Howell, MI (US); and Jin Shen, Northville, MI (US)
Assigned to GM GLOBAL TECHNOLOGY OPERATIONS, LLC, Detroit, MI (US)
Filed by GM GLOBAL TECHNOLOGY OPERATIONS LLC, Detroit, MI (US)
Filed on Sep. 30, 2020, as Appl. No. 17/038,615.
Prior Publication US 2022/0100167 A1, Mar. 31, 2022
Int. Cl. G05B 19/408 (2006.01); G06N 3/08 (2023.01)
CPC G05B 19/408 (2013.01) [G06N 3/08 (2013.01); G05B 2219/45076 (2013.01)] 16 Claims
OG exemplary drawing
 
1. A method for operating canister purge comprising:
obtaining a set of inputs, by a processor, pertaining to one or more features used to predict purge vapor characteristics of an intake system of a vehicle;
obtaining data, by the processor, from sensors about a vehicle's intake system for use by a neural network to enable the processor to classify the set of inputs comprising the one or more features for a purge flow control for use in predicting a presence of purge content in the vehicle's intake system, wherein the neural network comprises a convolution neural network (CNN) for classifying, by the processor, the set of inputs to predict the purge content in the vehicle's intake system;
obtaining, by the processor, an output from the neural network wherein the output is configured as a binary output to instruct a vehicle controller to execute an action of an injector fueling command;
applying, by the processor, a convolution function of a first, a second, and a third layer of the CNN to classify the set of inputs composed of the one or more features into one or more feature matrices with size reductions for configuring a fuel control action based on the binary output and
applying, by the processor, a first dense function to vectorize a feature matrix received from an output from the third layer wherein a first dense function flattens the feature matrix into a single connected vector for configuring the fuel control action based on the binary output.