Field operations system with particle filter
A method can include receiving channels of data from equipment responsive to operation of the equipment in an environment where the equipment and environment form a dynamic system; defining a particle filter that localizes a time window with respect to the channels of data; applying the particle filter at least in part by weighting particles of the particle filter using the channels of data, where each of the particles represents a corresponding time window; and selecting one of the particles according to its weight as being the time window of an operational state of the dynamic system.
1. A method comprising:
receiving channels of data from equipment responsive to operation of the equipment in an environment wherein the equipment and environment form a dynamic system;
defining a particle filter that localizes a time window with respect to the channels of data;
applying the particle filter at least in part by weighting particles of the particle filter using the channels of data, wherein each of the particles represents a corresponding time window;
selecting one of the particles according to its weight as being the time window of an operational state of the dynamic system; and
controlling the dynamic system based at least in part on the operational state.
2. The method of claim 1 , wherein the particle filter comprises a map simulated from operational procedure (OP) control signal instances and physical constraints.
3. The method of claim 1 , wherein the particles are characterized by a time window velocity.
4. The method of claim 1 , wherein the particle filter comprises a state transition model that depends on a time window velocity and changes in received channels of data with respect to time.
5. The method of claim 1 , wherein the weighting particles comprises using the channels of data and a deep Kalman filter.
6. The method of claim 5 , wherein the weighting particles is performed in a latent space defined in the deep Kalman filter.
7. The method of claim 1 , wherein the weighting particles is performed in a state space for representing states of the dynamic system.
8. The method of claim 1 , wherein the weighting particles utilizes a space that comprises a dimensionality that is greater than three.
9. The method of claim 8 , wherein the dimensionality depends on dimensionality of output of one or more recurrent layers of a neural network model of the dynamic system.
10. The method of claim 1 , wherein the operational state is a proscribed state of a pre-defined operational procedure.
11. The method of claim 1 , comprising outputting confidence of the selected one of the particles being the operational state.
12. The method of claim 1 , wherein the equipment comprises drilling equipment.
13. The method of claim 1 , wherein the equipment comprises sensors wherein the data are sensor data.
14. The method of claim 1 , wherein the channels of data comprise at least two channels of data.
15. The method of claim 14 , wherein the channels of data comprise block position data of a traveling block of a drilling rig.
16. A system comprising:
a processor;
memory accessible by the processor;
processor-executable instructions stored in the memory and executable to instruct the system to:
receive channels of data from equipment responsive to operation of the equipment in an environment wherein the equipment and environment form a dynamic system;
define a particle filter that localizes a time window with respect to the channels of data;
apply the particle filter at least in part by weighting particles of the particle filter using the channels of data, wherein each of the particles represents a corresponding time window;
select one of the particles according to its weight as being the time window of an operational state of the dynamic system; and
control at least one piece of equipment of the dynamic system based on the operational state.
17. One or more computer-readable storage media comprising processor-executable instructions to instruct a computing system to:
receive channels of data from equipment responsive to operation of the equipment in an environment wherein the equipment and environment form a dynamic system;
define a particle filter that localizes a time window with respect to the channels of data;
apply the particle filter at least in part by weighting particles of the particle filter using the channels of data, wherein each of the particles represents a corresponding time window;
select one of the particles according to its weight as being the time window of an operational state of the dynamic system; and
control at least one piece of equipment of the dynamic system based on the operational state.