Abstract: Methods and systems for adjusting operating parameters of a machine in anticipation of a transition from a current operational state to a predicted subsequent operational state. An electronic controller receives a data stream indicative of actuator settings, sensor outputs, and/or operator control settings and applies a pattern detection AI that is configured to determine a current operational state of the machine based on patterns detected in the data stream. The controller then applies a reinforcement learning AI that is configured to produce as an output one or more target operating parameters based at least in part on a predicted subsequent operational state of the machine. The one or more target operating parameters are applied to the machine and at least one performance metric of the machine is monitored. The reinforcement learning Ai is retrained based at least in part on the monitored performance metric(s).

Abstract: A work cycle detection and control system includes an angle detector that detects an angular position of an implement, operably coupled to a mobile machine, relative to a base of the mobile machine. The system also includes a range detector that detects a degree range of rotation, about the base, in which the angular position of the implement is located. Work cycle logic identifies a particular work cycle, from a plurality of different work cycles, that the mobile machine is performing, based on the degree range. An action signal generator generates an action signal, based on the particular work cycle.

Abstract: A mobile work machine includes a sensor configured to generate a sensor signal indicative of operation of the mobile work machine, a machine performance detection system configured to receive the sensor signal, generate a topological representation of the sensor signal, and determine a machine performance characteristic based on the topological representation relative to a reference model, and a control system configured to generate a control signal to control the mobile work machine based on the machine performance characteristic.

Abstract: Systems and methods are described for identifying a behavior of a machine. A computer system receives a signal indicative of operation of a field machine and applies a deep learning algorithm to identify a pattern in a collection of signals stored on a computer-readable memory. The collection of signals includes the received signal indicative of operation of the field machine and other signals. A series of targeted tests are performed using a test machine while monitoring a signal indicative of operation of the test machine. A behavior is identified during the series of targeted tests that produces a signal that matches the pattern identified by the deep learning algorithm. An occurrence of the behavior is then automatically identified in the field machine in response to detecting the pattern in the received signal indicative of operation of the field machine.

Abstract: A mobile work machine includes a sensor configured to generate a sensor signal indicative of operation of the mobile work machine, a machine performance detection system configured to receive the sensor signal, generate a topological representation of the sensor signal, and determine a machine performance characteristic based on the topological representation relative to a reference model, and a control system configured to generate a control signal to control the mobile work machine based on the machine performance characteristic.

Abstract: A machine output detection and control system includes machine metric logic that detects a plurality of quantity metrics, each quantity metric corresponding to sensor information associated with at least one mobile machine in a plurality of different mobile machines. The system also includes normalization logic that aggregates the plurality of different quantity metrics to generate, for each mobile machine, a normalized production unit that is normalized across the plurality of different mobile machines. Dependency logic correlates the normalized production unit, for each mobile machine, to a machine dependency that identifies an order in which the plurality of different mobile machines operate at a jobsite. Further, action signal logic generates an action signal, based on the correlation.

Abstract: A control system receives information indicative of characteristics of tree bundles that are felled at various locations in a forestry site. The control system receives information indicative of characteristics of the various machines that can be deployed at the forestry site. It includes a solution generation system that generates solutions indicative of which equipment should be deployed, to different locations in the forestry site, and particular routes over which the deployment is to occur. Control signals can be generated to control the equipment based on the generated solutions.

Abstract: Methods and systems for adjusting operating parameters of a machine in anticipation of a transition from a current operational state to a predicted subsequent operational state. An electronic controller receives a data stream indicative of actuator settings, sensor outputs, and/or operator control settings and applies a pattern detection AI that is configured to determine a current operational state of the machine based on patterns detected in the data stream. The controller then applies a reinforcement learning AI that is configured to produce as an output one or more target operating parameters based at least in part on a predicted subsequent operational state of the machine. The one or more target operating parameters are applied to the machine and at least one performance metric of the machine is monitored. The reinforcement learning Ai is retrained based at least in part on the monitored performance metric(s).

Abstract: Systems and methods are described for identifying a behavior of a machine. A computer system receives a signal indicative of operation of a field machine and applies a deep learning algorithm to identify a pattern in a collection of signals stored on a computer-readable memory. The collection of signals includes the received signal indicative of operation of the field machine and other signals. A series of targeted tests are performed using a test machine while monitoring a signal indicative of operation of the test machine. A behavior is identified during the series of targeted tests that produces a signal that matches the pattern identified by the deep learning algorithm. An occurrence of the behavior is then automatically identified in the field machine in response to detecting the pattern in the received signal indicative of operation of the field machine.

Abstract: A control system receives information indicative of characteristics of tree bundles that are felled at various locations in a forestry site. The control system receives information indicative of characteristics of the various machines that can be deployed at the forestry site. It includes a solution generation system that generates solutions indicative of which equipment should be deployed, to different locations in the forestry site, and particular routes over which the deployment is to occur. Control signals can be generated to control the equipment based on the generated solutions.

Abstract: A work cycle detection and control system includes an angle detector that detects an angular position of an implement, operably coupled to a mobile machine, relative to a base of the mobile machine. The system also includes a range detector that detects a degree range of rotation, about the base, in which the angular position of the implement is located. Work cycle logic identifies a particular work cycle, from a plurality of different work cycles, that the mobile machine is performing, based on the degree range. An action signal generator generates an action signal, based on the particular work cycle.

Abstract: A machine output detection and control system includes machine metric logic that detects a plurality of quantity metrics, each quantity metric corresponding to sensor information associated with at least one mobile machine in a plurality of different mobile machines. The system also includes normalization logic that aggregates the plurality of different quantity metrics to generate, for each mobile machine, a normalized production unit that is normalized across the plurality of different mobile machines. Dependency logic correlates the normalized production unit, for each mobile machine, to a machine dependency that identifies an order in which the plurality of different mobile machines operate at a jobsite. Further, action signal logic generates an action signal, based on the correlation.

Abstract: A system and method for computing histograms with exponential spacing of bins translates a fixed-point data sample that is to be placed in a bin to a floating-point representation (assuming the original data sample is not already in that particular format), estimates the base-2 logarithm of the floating-point representation, calculates an approximate histogram bin number based on the base-2 logarithm, and then adjusts the approximate bin number based on a comparison between the data sample and a data value associated with the approximate bin number.

Abstract: An engine cooling system (16) of a vehicle (12) includes a coolant de-gas bottle (30) which contains a body of liquid engine coolant (52). The vehicle (12) also has a second fluid system such as a fluid power assist steering system (70) or an engine lubricating oil system. The de-gas bottle (30) includes means for defining a second fluid passage (82) in the de-gas bottle for enabling flow of the second fluid through the de-gas bottle in a heat-exchanging relationship with the body of liquid engine coolant (52) in the de-gas bottle.