Virtual door sensor for transport unit
A method of providing a virtual door sensor for a transport unit is disclosed. The method includes monitoring operation of a transport climate control system for a climate controlled space to obtain transport climate control system operating data; transforming the transport climate control system operating data into door event model inputs; predicting a door event based on the obtained door event model inputs; and transmitting a notification according to the predicted door event.
1. A method of providing a virtual door sensor for a transport unit, the method comprising:
monitoring operation of a transport climate control system for a climate controlled space to obtain transport climate control system operating data, wherein the transport climate control system operating data includes power source data indicating an amount of power supplied to one or more components of the transport climate control system;
transforming the transport climate control system operating data, including the power source data, into door event model inputs;
predicting a door event based on the transformed door event model inputs, wherein predicting the door event includes applying the door event model inputs to a predictive data driven model; and
transmitting a notification according to the predicted door event,
wherein transforming the transport climate control system operating data includes eliminating data determined by the predictive data driven model to be less predictive of the door event by ranking the transport climate control system operating data by relevance to predicting the door event.
2. The method of claim 1 , wherein predicting the door event includes generating a probability of the door event based on the obtained door event model inputs and determining the door event has occurred when the probability of the door event exceeds a predetermined probability threshold.
3. The method of claim 1 , wherein transforming the transport climate control system operating data includes determining a gradient in the power source data over a period of time.
4. The method of claim 1 , wherein transforming the transport climate control system operating data, including the power source data, into door event model inputs includes at least one of: converting a data format of the transport climate control system operating data, removing corrupted or incomplete data points, combining different transport climate control system operating data according to a predetermined algorithm for creating more predictive variables, removing less relevant features or data categories.
5. The method of claim 1 ,
wherein the predictive data driven model provides a prediction output that includes a probability that a door is open at a given timestamp;
wherein predicting the door event further includes determining that the door is open by comparing the probability that the door is open at the given timestamp to a predetermined threshold; and
wherein the notification is transmitted according to the predicted door event upon determining that the probability exceeds the predetermined threshold.
6. The method of claim 1 , wherein the transport climate control system operating data include:
an operating parameter of the transport climate control system, and
an operating mode of the transport climate control system.
7. The method of claim 6 , wherein monitoring operation of the transport climate control system includes:
monitoring the operating parameter of the transport climate control system and the operating mode under which the transport climate control system being operated.
8. The method of claim 6 , further comprising:
obtaining the operating parameter from an operating parameter sensor and a controller in communication with the transport climate control system.
9. The method of claim 8 , wherein the operating parameter sensor is a temperature sensor disposed on a climate control circuit in thermal communication with the climate controlled space.
10. The method of claim 6 , wherein
the operating parameter includes a temperature setpoint within the climate controlled space, a return air temperature within the climate controlled space, and
the operating mode is a continuous cooling mode.
11. The method of claim 1 , further comprising
a machine learning algorithm training the predictive data driven model from the transport climate control system operating data with validated door event data.
12. The method of claim 1 , further comprises:
transmitting the transport climate control system operating data using a telematics system to a remote server in communication with the telematics system for obtaining the door event model inputs and predicting the door event.
13. The method of claim 1 , wherein
the notification is transmitted to a user interface.
14. The method of claim 1 , wherein the power source data includes at least one of a motor RPM of a motor providing power to the one or more components of the transport climate control system and a prime mover RPM of a prime mover providing power to the one or more components of the transport climate control system.
15. A virtual door sensor for a transport unit, the virtual door sensor comprising:
a controller configured to connect with a transport climate control system, and
a processing unit configured to connect with the controller, wherein the virtual door sensor is configured to:
monitor operation of the transport climate control system for a climate controlled space to obtain transport climate control system operating data using the controller, wherein the transport climate control system operating data includes power source data indicating an amount of power supplied to one or more components of the transport climate control system,
transform the transport climate control system operating data, including the power source data, into door event model inputs,
predict a door event with the processing unit based on the transformed door event model inputs, wherein predicting the door event includes entering the door event model inputs into a predictive data driven model, and
transmit a notification according to the predicted door event,
wherein transforming the transport climate control system operating data includes eliminating data determined by the predictive data driven model to be less predictive of the door event by ranking the transport climate control system operating data by relevance to predicting the door event.
16. The virtual door sensor of claim 15 , wherein the predictive data driven model provides a prediction output that includes a probability that a door is open at a given timestamp; and
wherein predicting the door event further includes determining that the door is open by comparing the probability that the door is open at the given timestamp to a predetermined threshold; and
wherein the notification is transmitted according to the predicted door event upon determining that the probability exceeds the predetermined threshold.
17. The virtual door sensor of claim 15 , further comprising
a sensor configured to provide the transport climate control system operating data transmitted to the controller.
18. The virtual door sensor of claim 15 , wherein
the transport climate control system operating data include an operating parameter output and an operating mode output.
19. The virtual door sensor of claim 15 , further comprising
a user interface configured to display the notification according to the predicted door event.
20. The virtual door sensor of claim 15 , further comprising
a physical door sensor configured to transmit physical door sensor output to the controller.
21. The virtual door sensor of claim 15 , wherein
the processing unit is configured to communicate with the controller via a telematics system over a cellular network.