TRANSMISSION CONTROL SYSTEM

• US 20130289836A1
• Filed: 04/27/2012
• Published: 10/31/2013
• Est. Priority Date: 04/27/2012
• Status: Abandoned Application

• Current Assignee: Caterpillar Incorporated
• Original Assignee: Caterpillar Incorporated
• Inventors: Li, Wei
• Application Number:
  US13/458,561
• Publication Number:
  US 20130289836A1
• Time in Patent Office: Days
• US Class Current: 701/51
• CPC Class Codes: B60W 10/30 including control of auxiliary equipment, e.g. air-conditioning compressors or oil pumps
• CPC Class Codes: B60W 30/1886 Controlling power supply to auxiliary devices
• CPC Class Codes: F16H 2061/0084 Neural networks

Abstract

A method of controlling a transmission associated with a machine includes determining a torque demand associated with a parasitic load, the parasitic load receiving power from a power source of the machine via the transmission. The method also includes converting the torque demand into a corresponding torque request using a first neural network associated with a control system of the machine. The torque demand is an input of the first neural network and the torque request is an output of the first neural network. The method further includes directing the power source to provide torque to the transmission substantially equal to the torque request.

Claims

1. A method of controlling a transmission associated with a machine, comprising:

determining a torque demand associated with a parasitic load, the parasitic load receiving power from a power source of the machine via the transmission;

converting the torque demand into a corresponding torque request using a first neural network associated with a control system of the machine, wherein the torque demand comprises an input of the first neural network and the torque request comprises an output of the first neural network; and

directing the power source to provide torque to the transmission substantially equal to the torque request.

2. The method of claim 1, further including determining an operating characteristic of at least one of the transmission, the power source, and the parasitic load, and converting the torque demand into the torque request based on the operating characteristic, wherein the operating characteristic comprises an additional input of the first neural network.

3. The method of claim 2, wherein the operating characteristic comprises one of power source speed, transmission speed, transmission gear, transmission speed ratio, and machine travel direction.

4. The method of claim 1, further including updating at least one component of the first neural network based on the torque request.

5. The method of claim 4, further including determining an additional torque demand associated with the parasitic load, and converting the additional torque demand into a corresponding additional torque request using the updated at least one component of the first neural network.

6. The method of claim 4, wherein the at least one component comprises a weight bias associated with a node of the first neural network.

7. The method of claim 1, wherein converting the torque demand into the torque request further includes determining, with the first neural network, a power loss of the transmission, the power loss characterizing performance of the transmission as the transmission receives torque provided by the power source.

8. The method of claim 1, further including determining a first torque value representative of torque provided to the transmission by the power source, and converting the first torque value into a corresponding second torque value using a second neural network associated with the control system, wherein the first torque value comprises an input of the second neural network and the second torque value comprises an output of the second neural network, the second torque value being representative of torque provided by the transmission in response to receiving torque from the power source substantially equal to the first torque value.

9. A method of controlling a transmission associated with a machine, comprising:

determining a plurality of operating characteristics of the machine;

determining a torque demand indicative of torque required by a traction device receiving power from the power source via the transmission;

inputting data indicative of the plurality of operating characteristics and the torque demand into a first neural network associated with a control system of the machine;

converting the torque demand into a torque request, based on the data, using the first neural network, the torque request being indicative of an input torque required by the transmission in order for the transmission to generate an output torque substantially equal to the torque demand; and

providing torque from the power source to the transmission substantially equal to the torque request.

10. The method of claim 9, further including converting at least one additional torque demand indicative of torque required by the traction device into at least one additional torque request, in a closed-loop manner, using the first neural network.

11. The method of claim 10, further including updating the first neural network based on the torque request, wherein the at least one additional torque demand is converted into the at least one additional torque request using the updated first neural network.

12. The method of claim 9, wherein converting the torque demand into the torque request further includes determining, with the first neural network, a power loss of the transmission, the power loss characterizing performance of the transmission as the transmission receives torque provided by the power source.

13. The method of claim 9, further including determining a first torque value representative of torque provided to the transmission by the power source, and converting the first torque value into a corresponding second torque value using a second neural network associated with the control system, wherein the first torque value comprises an input of the second neural network and the second torque value comprises an output of the second neural network, the second torque value being representative of torque provided by the transmission in response to receiving torque from the power source substantially equal to the first torque value.

14. The method of claim 13, further including updating the second neural network based on the second torque value;

determining a third torque value representative of torque provided to the transmission by the power source; and

converting the third torque value into a corresponding fourth torque value, in a closed-loop manner, using the updated second neural network.

15. The method of claim 9, wherein the first neural network comprises a plurality of nodes, the method further including inputting data indicative of each respective operating characteristic of the plurality of operating characteristics into a respective node of the plurality of nodes.

16. The method of claim 15, further including updating a weight bias associated with at least one node of the plurality of nodes based on the torque request.

17. A machine, comprising:

a power source;

a transmission operably connected to the power source;

a parasitic load receiving power from the power source via the transmission; and

a control system in communication with the power source, the transmission, and the parasitic load, wherein the control system is operable to

determine a torque demand associated with the parasitic load;

convert the torque demand into a corresponding torque request using a first neural network associated with the control system, wherein the torque demand comprises an input of the first neural network and the torque request comprises an output of the first neural network; and

direct the power source to provide torque to the transmission substantially equal to the torque request.

18. The machine of claim 17, wherein the parasitic load comprises a traction device of the machine.

19. The machine of claim 17, wherein the power source comprises a diesel engine, and the transmission comprises one of an electric continuously variable transmission and a hydraulic continuously variable transmission, the system further including at least one sensor configured to determine an operating characteristic of the diesel engine and to direct a signal indicative of the operating characteristic to the control system.

20. The machine of claim 19, wherein the torque demand is converted into the torque request, using the first neural network, based on the signal.