Shift detection system and method for a power supply system

Patent metadata

Field	Value
Publication number	US-12510869-B2
Application number	US-202318297834-A
Country	US
Kind code	B2
Filing date	Apr 10, 2023
Priority date	Apr 26, 2022
Publication date	Dec 30, 2025
Grant date	Dec 30, 2025

Abstract

A shift detection system and method may monitor at least first and second operating parameters of a power supply system over time, and generate an adaptive model based on values of the first and second operating parameters. The adaptive model may include data points defined by the values of the first and second operating parameters. The data points may be grouped into bins according to designated ranges of the first operating parameter, and nodes may be calculated for individual bins based on the data points within the bins. An output function may be determined based on the nodes, and a shift incident may be detected based at least in part on an offset between the output function and recent values of the second operating parameter. A control signal may be generated in response to the shift incident to control the power supply system and/or notify an operator.

First claim

What is claimed is:

1 . A shift detection system comprising:
a controller comprising one or more processors and configured to:
obtain values of a first operating parameter of a power supply system and values of a second operating parameter of a power supply system, the first and second operating parameters monitored over time as the power supply system operates;
generate an adaptive model based on the values of the first and second operating parameters that are monitored, the adaptive model comprising a plurality of data points with each of the data points defined by a respective value of the first operating parameter and a respective value of the second operating parameter, the controller configured to group the data points into bins according to designated ranges of the first operating parameter and calculate nodes associated with individual bins based on the data points within the individual bins, the controller configured to determine an output function based on the nodes which represents a relationship between the first and second operating parameters;
detect a shift incident based at least in part on an offset between the output function of the adaptive model and values of the second operating parameter as monitored; and
responsive to detecting the shift incident, generate a control signal to one or more of (i) notify an operator that the power supply system is at risk of damage; (ii) initiate maintenance for the power supply system; (iii) apply an operating constraint on the power supply system; or (iv) shut down the power supply system.

2 . The shift detection system of claim 1 , wherein the controller is configured to detect the shift incident by inputting the offset into a change detection algorithm to detect a mean shift in the data points outside of a designated margin surrounding the output function.

3 . The shift detection system of claim 2 , wherein the change detection algorithm integrates the data points outside of the designated margin, and the controller is configured to detect the shift incident in response to an output signal of the change detection algorithm exceeding a threshold value.

4 . The shift detection system of claim 3 , wherein the change detection algorithm is a cumulative sum control (CUSUM) algorithm.

5 . The shift detection system of claim 1 , wherein the controller is configured to detect the shift incident by detecting a mean shift in the values of the second operating parameter by at least one standard deviation relative to the output function of the adaptive model.

6 . The shift detection system of claim 1 , wherein the controller is configured to determine the output function of the adaptive model by performing a linear interpolation that connects the nodes.

7 . The shift detection system of claim 1 , wherein each of the nodes is located at a center of the data points within the associated bin, and the controller is configured to determine each of the nodes by calculating a first mean of the values of the first operating parameter of the data points within the associated bin, calculating a second mean of the values of the second operating parameter of the data points within the associated bin, and classifying the first mean and the second mean as coordinates of the node.

8 . The shift detection system of claim 7 , wherein the first mean and the second mean are weighted means, and the controller is configured to calculate the first mean and the second mean by incorporating a forgetting factor that applies greater weight to the data points that are more recent and less weight to the data points that are less recent.

9 . The shift detection system of claim 1 , wherein the controller is configured to postpone calculating a respective node in each of the individual bins until there is at least a threshold number of the data points within the individual bin.

10 . The shift detection system of claim 1 , wherein the controller is configured to determine a time at which the shift incident occurred, and to generate a second control signal that logs a record of the shift incident including the time of the shift incident.

11 . The shift detection system of claim 1 , wherein the power supply system is operable in both a diesel mode, in which the power supply system uses petroleum-derived diesel fuel, and an alternative fuel mode, in which the power supply system uses another type of fuel, and the controller is configured to generate the control signal to apply the operating constraint on the power supply system by restricting operation of the power supply system to the diesel mode only.

12 . The shift detection system of claim 1 , wherein the first operating parameter is a flow rate of exhaust gas emitted from the power supply system and the second operating parameter is pressure in a crankcase of the power supply system.

13 . The shift detection system of claim 1 , further comprising one or more sensors operably connected to the controller, the one or more sensors configured to generate sensor measurements used by the controller to monitor the first and second operating parameters.

14 . The shift detection system of claim 1 , wherein the power supply system is an engine or fuel cell that powers propulsion of a vehicle.

15 . The shift detection system of claim 14 , wherein the controller is disposed onboard the vehicle.

16 . A method comprising:
monitoring a first operating parameter and a second operating parameter of a power supply system over time as the power supply system operates; generating an adaptive model based on values of the first and second operating parameters that are monitored, the adaptive model comprising a plurality of data points with each of the data points defined by a respective value of the first operating parameter and a respective value of the second operating parameter, generating the adaptive model comprises grouping the data points into bins according to designated ranges of the first operating parameter and calculating nodes associated with individual bins based on the data points within the individual bins, generating the adaptive model comprises determining an output function based on the nodes which represents a relationship between the first and second operating parameters; detecting a shift incident based at least in part on an offset between the output function of the adaptive model and values of the second operating parameter as monitored; and responsive to detecting the shift incident, generating a control signal to one or more of (i) notify an operator that the power supply system is at risk of damage; (ii) initiate maintenance for the power supply system; (iii) apply an operating constraint on the power supply system; or (iv) shut down the power supply system.

17 . The method of claim 16 , wherein detecting the shift incident comprises inputting the offset into a cumulative sum control (CUSUM) algorithm to detect a mean shift in the data points outside of a designated margin surrounding the output function.

18 . The method of claim 16 , wherein determining the output function of the adaptive model comprises performing a linear interpolation that connects the nodes.

19 . The method of claim 16 , wherein each of the nodes is located at a center of the data points within the associated bin, and calculating the nodes comprises calculating a first mean of the values of the first operating parameter of the data points within the associated bin and a second mean of the values of the second operating parameter of the data points within the associa

Assignees

• Transp Ip Holdings Llc

Inventors

• Pedder Jacob Kenneth

Classifications

• G05B13/045

  using a perturbation signal · CPC title

• G05B13/0265

  the criterion being a learning criterion · CPC title

• G05B2219/2637

  Vehicle, car, auto, wheelchair · CPC title

• G05B23/024

  Quantitative history assessment, e.g. mathematical relationships between available data; Functions therefor; Principal component analysis [PCA]; Partial least square [PLS]; Statistical classifiers, e.g. Bayesian networks, linear regression or correlation analysis; Neural networks · CPC title

• G05B13/041 Primary

  in which a variable is automatically adjusted to optimise the performance · CPC title