Systems and methods for system optimization and/or failure detection
Implementations of a system configured for operation of a motor may include a motor controller coupled with a memory, the motor controller configured to be coupled with a motor. The motor controller may be configured to store a set of control parameters in the memory, the set of control parameters generated using a deep reinforcement learning agent and data associated with one or more parameters of the motor. The set of control parameters may be configured to define an optimized operating area for the motor.
1. A system configured for operation of a motor, the system comprising:
a motor controller coupled with a memory, the motor controller configured to be coupled with a motor; and
a power factor controller coupled with the motor controller;
wherein the motor controller is configured to store a set of control parameters in the memory, the set of control parameters generated using a deep reinforcement learning agent and data associated with one or more parameters of the motor;
wherein the set of control parameters are configured to define an operating area for the motor;
wherein the power factor controller and the motor controller communicate bidirectionally; and
wherein the deep reinforcement learning agent is trained using data from the power factor controller.
2. The system of claim 1 , wherein the motor controller is configured to be coupled with a telecommunication network and wherein the telecommunication network is configured to be operatively coupled with a cloud computing system which is configured to comprise the deep reinforcement learning agent and use the deep reinforcement learning agent and the data associated with the one or more parameters of the motor to generate the set of control parameters and then communicate the set of control parameters across the telecommunication network to the motor controller for storing in the memory.
3. The system of claim 1 , wherein the deep reinforcement learning agent is comprised in the memory and the motor controller is configured to use the deep reinforcement learning agent and the data associated with one or more parameters of the motor to generate the set of control parameters.
4. The system of claim 1 , wherein the deep reinforcement learning agent is comprised in the memory and is configured to communicate with a cloud computing system over a telecommunication network coupled with the motor controller where the cloud computing system is configured to use the data associated with one or more parameters of the motor to generate a set of agent control parameters used by the deep reinforcement agent to generate the set of control parameters associated with the operating area for the motor.
5. The system of claim 1 , further comprising two or more motor controllers each coupled with a memory and each configured to be coupled with a corresponding motor,
wherein the memory coupled with each motor controller comprises a set of control parameters for that motor controller where the set of control parameters define an operating area for the corresponding motor, and wherein the set of control parameters for each motor controller is determined by executing a second deep reinforcement learning agent using data associated with one or more parameters of each motor associated with each motor controller.
6. The system of claim 1 , wherein the deep reinforcement learning agent is one of a deep Q-network, a double deep Q-network, an Actor-Critic agent, a policy gradient agent, a Monte Carlo tree search agent, an imitation learning agent, or any combination thereof.
7. The system of claim 1 , wherein the deep reinforcement learning agent is generated using a deep neural network and a Markov decision process.
8. The system of claim 1 , wherein the motor controller is configured to use the set of control parameters to provide one or more instructions to the power factor controller and wherein the power factor controller is configured to use the set of control parameters to provide one or more instructions to the motor controller.
9. A method of controlling a motor, the method comprising:
providing a motor controller coupled with a memory, the motor controller coupled with a power factor controller, the motor controller also configured to be coupled with a motor; and
storing a set of control parameters in the memory, the set of control parameters generated using a deep reinforcement learning agent and data associated with one or more parameters of the motor;
wherein the set of control parameters are configured to define an operating area for the motor;
wherein the power factor controller and the motor controller communicate bidirectionally; and
wherein the deep reinforcement learning agent is trained using data from the power factor controller.
10. The method of claim 9 , wherein the motor controller is configured to be coupled with a telecommunication network and wherein the telecommunication network is configured to be operatively coupled with a cloud computing system which is configured to comprise the deep reinforcement learning agent and use the deep reinforcement learning agent and the data associated with the one or more parameters of the motor to generate the set of control parameters and then communicate the set of control parameters across the telecommunication network to the motor controller for storing in the memory.
11. The method of claim 9 , wherein the deep reinforcement learning agent is comprised in the memory and the motor controller uses the deep reinforcement learning agent and the data associated with one or more parameters of the motor to generate the set of control parameters.
12. The method of claim 9 , wherein the deep reinforcement agent is comprised in the memory and is configured to communicate with a cloud computing system over a telecommunication network coupled with the motor controller where the cloud computing system uses the data associated with one or more parameters of the motor to generate a set of agent control parameters used by the deep reinforcement agent to generate the set of control parameters associated with the operating area for the motor.
13. The method of claim 12 , further comprising at least a second deep reinforcement agent configured to use the set of agent control parameters to generate a portion of the set of control parameters associated with the operating area for the motor.
14. The method of claim 9 , wherein the deep reinforcement learning agent is one of a deep Q-network, a double deep Q-network, an Actor-Critic agent, a policy gradient agent, a Monte Carlo tree search agent, an imitation learning agent, or any combination thereof.
15. The method of claim 9 , wherein the deep reinforcement learning agent is generated using a deep neural network and a Markov decision process.
16. The method of claim 9 , wherein the motor controller uses the set of control parameters to provide one or more instructions to the power factor controller and wherein the power factor controller uses the set of control parameters to provide one or more instructions to the motor controller.
17. A system configured for operation of a motor, the system comprising:
a motor controller coupled with a memory, the motor controller configured to be coupled with a motor; and
a power factor controller coupled with the motor controller;
wherein the motor controller is configured to store a set of control parameters in the memory, the set of control parameters generated using a deep reinforcement learning agent and data associated with one or more parameters of the motor;
wherein the set of control parameters are configured to define an operating area for the motor;
wherein the power factor controller and the motor controller communicate bidirectionally;
wherein the deep reinforcement learning agent is trained using data from the power factor controller; and
wherein the motor controller uses the set of control parameters to provide one or more instructions to the power factor controller.
18. The system of claim 17 , wherein the motor controller is configured to be coupled with a telecommunication network and wherein the telecommunication network is configured to be operatively coupled with a cloud computing system which is configured to comprise the deep reinforcement learning agent and use the deep reinforcement learning agent and the data associated with the one or more parameters of the motor to generate the set of control parameters and then communicate the set of control parameters across the telecommunication network to the motor controller for storing in the memory.
19. The system of claim 17 , wherein the set of control parameters are generated using the deep reinforcement learning agent and a second deep reinforcement learning agent.
20. The system of claim 19 , wherein the set of control parameters are configured to define an operating area for a single motor.