Abstract: A system and method that include receiving sensor data during drilling of a portion of a borehole in a geologic environment. The system and method also include selecting a drilling mode from a plurality of drilling modes based at least on a portion of the sensor data. The system and method additionally include simulating drilling of the borehole using the selected drilling mode in a multi-dimensional spatial environment to generate a simulated state of the borehole in the geologic environment. The system and method further include analyzing the simulated state of the borehole and generating a reward using the simulated state of the borehole and a planned borehole trajectory and using the reward to train an agent to provide automated directional drilling with transitions between at least one of: a plurality of drilling modes and a plurality of toolface settings.

Abstract: A method can include receiving real-time data during a drilling operation performed by a drillstring that includes a mud motor and a bit characterized by an expected performance profile; determining actual performance of the drillstring based at least in part on the real-time data; predicting degraded performance of the drillstring based at least in part on the real-time data and a mud motor degradation model; and updating the expected performance profile based on a comparison of the actual performance and the degraded performance.

Abstract: A method can include receiving sensor data during drilling of a portion of a borehole in a geologic environment; determining a drilling mode from a plurality of drilling modes using a trained neural network and at least a portion of the sensor data; and issuing a control instruction for drilling an additional portion of the borehole using the determined drilling mode.

Abstract: A system and method that include receiving sensor data acquired during execution of a drilling operation workflow and generating state information of a wellsite system and receiving contextual information for a role associated with a workflow that includes one or more tasks of the workflow. The system and method also include generating a natural language report based at least in part on the state information and based at least in part on the contextual information to facilitate planning and execution of the one or more tasks of the workflow. The system and method further include transmitting the natural language report via a network interface based at least in part on an identifier associated with the role and presenting a graphical user interface that renders information as to the planning and execution of the one or more tasks of the workflow to achieve a desired state of the wellsite system.

Abstract: A system and method that include receiving sensor data during drilling of a portion of a borehole in a geologic environment. The system and method also include selecting a drilling mode from a plurality of drilling modes based at least on a portion of the sensor data. The system and method additionally include simulating drilling of the borehole using the selected drilling mode and generating a state of the borehole in the geologic environment based on the simulated drilling of the borehole. The system and method further include generating a reward using the state of the borehole and a planned borehole trajectory and using the reward through deep reinforcement learning to maximize future rewards for drilling actions.

Abstract: A method can include receiving state information for a wellsite system; receiving contextual information for a role associated with a workflow; generating a natural language report based at least in part on the state information and based at least in part on the contextual information; and transmitting the natural language report via a network interface based at least in part on an identifier associated with the role.

Abstract: A system and method that can include training a deep neural network using time series data that represents functions of a non-linear Kalman filter that represents a dynamic system of equipment and environment and models a pre-defined operational procedure as a temporal sequence. The system and method can also include receiving operation data from the equipment responsive to operation in the environment and outputting an actual operation as an actual sequence of operational actions by the deep neural network. The system and method can additionally include performing an operation-level comparison to evaluate the temporal sequence against the actual sequence using a distance function in a latent space of the deep neural network and outputting a score function that quantifies the distance function in the latent space. The system and method can further include controlling an electronic component to execute an electronic operation based on the score function.

Abstract: A method can include training a deep neural network to generate a trained deep neural network where the trained deep neural network represents functions of a nonlinear Kalman filter that represents a dynamic system of equipment and environment via an internal state vector of the dynamic system; generating a base internal state vector, that corresponds to a pre-defined operational procedure, using the trained deep neural network; receiving operation data from the equipment responsive to operation in the environment; generating an internal state vector using the operation data and the trained deep neural network; and comparing at least the internal state vector to at least the base internal state vector.

Abstract: A method can include receiving multi-channel time series data of drilling operations; training a deep neural network (DNN) using the multi-channel time series data to generate a trained deep neural network as part of a computational simulator where the deep neural network includes at least one recurrent unit; simulating a drilling operation using the computational simulator to generate a simulation result; and rendering the simulation result to a display.

Abstract: 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.

Abstract: A method can include, during drilling operations at a wellsite, receiving operational data, where the data include hookload data, surface rotation data and block position data; training a controller using the hookload data, the surface rotation data and the block position data for determination of one or more transition thresholds, where the transitions thresholds include an in-slips to out-of-slips transition threshold and an out-of-slips to in-slips transition threshold; during the drilling operations, receiving additional operational data that include additional hookload data; and storing at least a portion of the additional operational data in association with slips state as determined based at least in part on a comparison of at least a portion of the additional hookload data and at least one of the determined transition thresholds.

Abstract: A method includes acquiring data during rig operations where the rig operations include operations that utilize a bit to drill rock and where the data include different types of data; analyzing the data utilizing a probabilistic mixture model for modes, a detection engine for trends and a network model for an inference based at least in part on at least one of a mode and a trend; and outputting information as to the inference where the inference characterizes a relationship between the bit and the rock.

Abstract: A method can include, during drilling operations at a wellsite, receiving operational data, where the data include hookload data, surface rotation data and block position data; training a controller using the hookload data, the surface rotation data and the block position data for determination of one or more transition thresholds, where the transitions thresholds include an in-slips to out-of-slips transition threshold and an out-of-slips to in-slips transition threshold; during the drilling operations, receiving additional operational data that include additional hookload data; and storing at least a portion of the additional operational data in association with slips state as determined based at least in part on a comparison of at least a portion of the additional hookload data and at least one of the determined transition thresholds.

Abstract: A method can include acquiring data associated with a field operation in a geologic environment; processing the data by partitioning operationally and representing symbolically; formulating a symbolic query for an operating procedure specification; performing a search of the symbolically represented data utilizing the symbolic query and a probabilistic chain model; receiving a search result responsive to the search; assessing compliance with the operation procedure specification utilizing the search result; and issuing a control signal to field equipment utilizing the assessment of compliance.

Abstract: A method includes acquiring data during rig operations where the rig operations include operations that utilize a bit to drill rock and where the data include different types of data; analyzing the data utilizing a probabilistic mixture model for modes, a detection engine for trends and a network model for an inference based at least in part on at least one of a mode and a trend; and outputting information as to the inference where the inference characterizes a relationship between the bit and the rock

Abstract: A method can include receiving state information for a wellsite system; receiving contextual information for a role associated with a workflow; generating a natural language report based at least in part on the state information and based at least in part on the contextual information; and transmitting the natural language report via a network interface based at least in part on an identifier associated with the role.

Abstract: A method can include training a deep neural network to generate a trained deep neural network where the trained deep neural network represents functions of a nonlinear Kalman filter that represents a dynamic system of equipment and environment via an internal state vector of the dynamic system; generating a base internal state vector, that corresponds to a pre-defined operational procedure, using the trained deep neural network; receiving operation data from the equipment responsive to operation in the environment; generating an internal state vector using the operation data and the trained deep neural network; and comparing at least the internal state vector to at least the base internal state vector.

Abstract: A drilling rig site may include at least one tubular configured to be inserted into a wellbore at the drilling rig, at least one imaging device configured to detect a location of an end of the at least one tubular or a feature of the at least one tubular, and a processor receiving an input from the at least one imaging device and configured to calculate a distance between the end of the at least one tubular and another element, a diameter of the at least one tubular, or movement of the at least one tubular. A method for completing a drilling operation at a rig site, may include capturing an image of a tubular at a rig site, the tubular configured to be inserted into a wellbore at the rig site, detecting a location of an end of the tubular or a feature of the tubular from the image, and determining a diameter of the tubular, a distance between the detected end of the tubular and another element, or movement of the tubular.

Abstract: A method can include receiving state information for a wellsite system; receiving contextual information for a role associated with a workflow; generating a natural language report based at least in part on the state information and based at least in part on the contextual information; and transmitting the natural language report via a network interface based at least in part on an identifier associated with the role.

Abstract: A method can include receiving sensor data during drilling of a portion of a borehole in a geologic environment; determining a drilling mode from a plurality of drilling modes using a trained neural network and at least a portion of the sensor data; and issuing a control instruction for drilling an additional portion of the borehole using the determined drilling mode.