Method and apparatus for detecting key-on and key-off states using time-to-frequency transforms

Patent metadata

Field	Value
Publication number	US-2015191138-A1
Application number	US-201414150018-A
Country	US
Kind code	A1
Filing date	Jan 8, 2014
Priority date	Jan 8, 2014
Publication date	Jul 9, 2015
Grant date	—

Abstract

A key state detector for a vehicle collects a sequence of battery voltage samples and applies a time-domain to frequency-domain transform (TFT) to the collected samples. The results of the TFT are then applied to an artificial neural network (ANN) to determine if they represent a key-on or key-off state. The ANN is trained based on data collected from the vehicle and is periodically retrained so that the detection of key-on and key-off states conforms to the particular vehicle and tracks the aging of vehicle components

First claim

What is claimed is:

1 . A method for determining the key state of a vehicle comprising:
a) collecting a sequence of battery voltage samples for the vehicle; b) calculating a time-domain to frequency-domain transform (TFT) for the collected samples to produce a set of frequency domain features; c) applying the set of frequency domain features to an artificial neural network (ANN) to determine the key state of the vehicle; and repeating steps a), b) and c) at predetermined intervals to monitor a current key state of the vehicle.

2 . The method of claim 1 , further comprising:
confirming that each key state determined by the ANN is correct by monitoring at least one of movement and speed of the vehicle and when a key state is not confirmed, toggling the determined key state.

3 . The method of claim 2 wherein the key state is confirmed by monitoring movement of the vehicle using an accelerometer and by monitoring speed of the vehicle using a signal provided by an on-board diagnostic (OBD) system of the vehicle.

4 . The method of claim 2 , wherein the key state is confirmed by monitoring movement and speed of the vehicle using a GPS receiver.

5 . The method of claim 2 , further comprising:
storing, as training data, each set of frequency domain features and respective determined key state; and training the ANN using the training data after a predetermined amount of training data has been stored.

6 . The method of claim 5 , wherein the ANN is a one hidden layer feed-forward network and the training includes applying the training data to the ANN and adjusting coefficients and biases of the ANN responsive to the applied training data to reduce differences between the key states detected by the ANN and the respective key states of the training data.

7 . The method of claim 1 , further comprising:
for a predetermined number of key-state determinations prior to using the ANN to determine the key state:
determining the key state of the vehicle by comparing the battery voltage to a threshold;
collecting a sequence of battery voltage samples for the vehicle;
calculating the TFT for the collected samples to produce a set of frequency domain features; and
storing the collected set of frequency domain features with the respective determined key state as training data; and
after the predetermined number of key state determinations, training the ANN using the stored training data.

8 . The method of claim 1 , wherein the calculating of the TFT includes calculating at least one of a Fourier transform, a fast Fourier transform (FFT), a wavelet transform, a discrete wavelet transform (DWT), a discrete cosine transform (DCT) and a Hadamard transform.

9 . Apparatus for determining the key state of a vehicle comprising:
an analog-to-digital converter (ADC) for sampling a battery voltage of the vehicle at predetermined intervals to collect respective sets of digitized battery voltage samples; a sample memory coupled to the ADC to store the collected sets of samples; a processor configured to calculate a time-domain to frequency-domain transform (TFT) for each set of samples to produce respective sets of frequency domain features; an artificial neural network (ANN) coupled to the processor to sequentially process the sets of frequency domain features to determine the key state of the vehicle.

10 . The apparatus of claim 9 , further including:
an accelerometer; and a satellite positioning system (SPS) receiver; wherein the processor is further configured to confirm that each key state determined by the ANN is correct by monitoring at least one of movement and speed of the vehicle responsive to the accelerometer and the SPS receiver and when a key state is not confirmed, to toggle the determined key state.

11 . The apparatus of claim 10 , further comprising:
a training memory, coupled to the processor to store, as training data, each set of frequency domain features and respective determined key state for each confirmed key state; wherein the processor is configured to train the ANN using the training data after a predetermined amount of training data has been stored.

12 . The apparatus of claim 11 , wherein the ANN is a one hidden layer feed-forward network and the processor is configured to apply the training data to the ANN and adjusting coefficients and biases of the ANN responsive to the applied training data.

13 . The apparatus of claim 9 , wherein the processor is further configured to:
for a predetermined number of key-state determinations prior to using the ANN to determine the key state:
determine the key state of the vehicle by comparing the battery voltage to a threshold;
collect a sequence of battery voltage samples for the vehicle;
calculate the TFT for the collected samples to produce a set of frequency domain features; and
store the collected set of frequency domain features with the respective determined key state as training data in the training memory;
wherein the processor is configured to train the ANN using the stored training data after a predetermined amount of training data has been stored.

14 . The apparatus of claim 10 , wherein the processor is configured to calculate the TFT by calculating at least one of a Fourier transform, a fast Fourier transform (FFT), a wavelet transform, a discrete wavelet transform (DWT), a discrete cosine transform (DCT) and a Hadamard transform.

15 . A non-transitory computer readable medium including computer programming instructions configured to cause a processor to:
collect a plurality of sets of battery voltage samples for a vehicle; calculate, for each set of battery voltage samples, a time-domain to frequency-domain transform (TFT) to produce a respective set of frequency domain features; apply each set of frequency domain features to an artificial neural network (ANN) to determine the key state of the vehicle.

16 . The computer readable medium of claim 15 , wherein the computer programming instructions further cause the processor to confirm that each key state determined by the ANN is correct by monitoring at least one of movement and speed of the vehicle and when a key state is not confirmed, to toggle the determined key state.

17 . The computer readable medium of claim 16 , wherein the computer programming instructions further cause the processor to:
store, as training data, each set of frequency domain features and respective determined key state; and train the ANN using the training data after a predetermined amount of training data has been stored.

18 . The computer readable medium of claim 17 , wherein computer programming instructions are configured to cause the processor to implement the ANN as a one hidden layer feed-forward network.

19 . The computer readable medium of claim of claim 15 , wherein the computer programming instructions are configured to cause the processor to:
for a predetermined number of key-state determinations prior to using the ANN to determine the key state: determine the key state of the vehicle by comparing the battery voltage to a threshold; collect a sequence of battery voltage samples for the vehicle; calculate the TFT for the collected samples to produce a set of frequency domain features; and store the collected set of frequency domain features with the respective determined key state as training data; and after the predetermined number of key state determinations, train the ANN using the stored training data.

20 . The computer readable medium of

Assignees

• Verizon Patent & Licensing Inc

Inventors

• Quintero Francisco

Classifications

• B60R16/0231 Primary

  Circuits relating to the driving or the functioning of the vehicle (monitoring tyres B60C23/00; indicating overspeed B60K31/00; for dash boards B60K37/00, B60Q3/10; for indicating emergencies B60Q1/52; brake control systems B60T; registering or indicating the working of vehicles G07C5/00; measuring distance G01C, e.g. combinations of speed and distance G01C23/00; engine indicators G01L; measuring speed or acceleration G01P) · CPC title

• B60W2520/10

  Longitudinal speed · CPC title