Granted Patent B2

US 12,499,377 · App. 17/217,071 · Granted Dec 16, 2025

Inventors: Stephanie Deckas Benson (Prior Lake, MN); Wahid El Chaar (Burnsville, MN)

Assignee: THERMO KING LLC

G06N5/04B60H1/3225G05B23/0254G06N20/00

Abstract

Claims (63)

1 . A method for predicting an impending climate control failure for a transport climate control system (TCCS), the method comprising:

a plurality of sensors sensing one or more operational parameters;

one or more controllers determining one or more control parameters;

a backend obtaining the one or more operational parameters and/or the one or more control parameters of transport climate control systems including the TCCS;

the backend obtaining service records for the transport climate control systems;

training a machine learning model with the service records for the transport climate control systems, and at least one of the one or more operational parameters of the transport climate control systems or the one or more control parameters of the transport climate control systems;

transforming the one or more operational parameters and/or the one or more control parameters for training the machine learning model by applying a data window based on timestamp of each of the one or more operational parameters and/or the one or more control parameters;

deploying the trained machine learning model;

predicting the impending climate control failure for the TCCS using the trained machine learning model, the one or more operational parameters of the TCCS, and/or the one or more control parameters of the TCCS;

transforming the predicted impending climate control failure into a warning;

determining maintenance on the TCCS being performed based on the warning;

determining a repair of the TCCS being conducted based on the performed maintenance; and

determining feedback based on the performed maintenance,

wherein training the machine learning model includes training the machine learning model with the determined feedback.

2 . The method of claim 1 , wherein the backend obtaining the one or more operational parameters and/or the one or more control parameters of transport climate control systems includes:

telematics communicating the one or more operational parameters and/or the one or more control parameters of the transport climate control systems to the backend.

3 . The method of claim 1 , wherein training the machine learning model includes:

deriving features from the one or more operational parameters of the transport climate control systems, and/or the one or more control parameters of the transport climate control systems, and the service records for the transport climate control systems;

generating aggregated features based on the derived features;

determining feeding features based on the aggregated features; and

training the machine learning model with the feeding features.

4 . The method of claim 3 , wherein the derived features include one or more of a difference between a return air temperature and a discharge air temperature, an ambient setpoint differential, a return air setpoint differential, and a thermodynamic coefficient of performance.

5 . The method of claim 3 , further comprising:

determining alarm data during a predetermined window; and

deriving unit features for the transport climate control systems,

wherein training the machine learning model includes training the machine learning model with the feeding features, the alarm data, and the derived unit features.

6 . The method of claim 1 , further comprising:

alerting a recipient the warning through an electronic communication.

7 . The method of claim 1 , further comprising:

determining a failure rate of the predicted impending climate control failure; and

when the failure rate exceeds a predetermined threshold, retraining the machine learning model.

8 . The method of claim 1 , further comprising:

obtaining field failure events for the TCCS; and

when the field failure events do not match the predicted impending climate control failure, retraining the machine learning model.

9 . The method of claim 1 , further comprising:

after predicting the impending climate control failure for the TCCS, obtaining a first set of the one or more operational parameters and/or the one or more control parameters of the TCCS during a first predetermined period of time; and

obtaining a second set of the one or more operational parameters and/or the one or more control parameters of the TCCS during a second predetermined period of time;

when a difference between the first set and the second set exceeds a predetermined threshold, retraining the machine learning model.

10 . The method of claim 1 , wherein the predicted impending climate control failure for the TCCS includes one or more of compressor failures, refrigerant leaks, expansion valve failures, evaporate coil failures, condenser coil failures, idler assembly failures, tensioner failures, belt failures, alternator failures, and battery failures.

11 . The method of claim 1 , wherein the one or more operational parameters and/or the one or more control parameters of transport climate control systems include an electronic throttling valve position, a suction pressure, and a discharge pressure.

12 . The method of claim 1 , wherein the one or more operational parameters and/or the one or more control parameters of transport climate control systems include an ambient temperature, a shunt current, and a battery voltage; and

the predicted impending climate control failure for the TCCS includes battery failures.

13 . The method of claim 1 ,

wherein the performed maintenance is a predictive maintenance.

14 . A method for predicting an impending climate control failure for a transport climate control system (TCCS), the method comprising:

a plurality of sensors sensing one or more operational parameters;

one or more controllers determining one or more control parameters;

a backend obtaining the one or more operational parameters and/or the one or more control parameters of transport climate control systems including the TCCS;

the backend obtaining service records for the transport climate control systems;

training a machine learning model with the service records for the transport climate control systems, and at least one of the one or more operational parameters of the transport climate control systems or the one or more control parameters of the transport climate control systems;

transforming the one or more operational parameters and/or the one or more control parameters for training the machine learning model by applying a data window based on timestamp of each of the one or more operational parameters and/or the one or more control parameters;

deploying the trained machine learning model;

predicting the impending climate control failure for the TCCS using the trained machine learning model, the one or more operational parameters of the TCCS, and/or the one or more control parameters of the TCCS;

transforming the predicted impending climate control failure into a warning;

determining maintenance on the TCCS being performed based on the warning; and

determining a repair of the TCCS being conducted based on the performed maintenance, the method further comprising:

determining a failure rate of the predicted impending climate control failure, and when the failure rate exceeds a predetermined threshold, retraining the machine learning model; or

obtaining field failure events for the TCCS, and when the field failure events do not match the predicted impending climate control failure, retraining the machine learning model; or

after predicting the impending climate control failure for the TCCS, obtaining a first set of the one or more operational parameters and/or the one or more control parameters of the TCCS during a first predetermined period of time, obtaining a second set of the one or more operational parameters and/or the one or more control parameters of the TCCS during a second predetermined period of time, and when a difference between the first set and the second set exceeds a predetermined threshold, retraining the machine learning model.

15 . The method of claim 1 , further comprising:

transforming the service records with one or more timestamps to produce features for training the machine learning model.

16 . The method of claim 1 , further comprising:

tuning parameters of the machine learning model based on a risk tolerance to adjust the machine learning model.

Assignments (2)

Continuity (1)

References Cited (11)