A board production management device for managing a board production line including a solution memory section for linking and storing a problem event that may occur in a board production line and that requires a countermeasure operation, a solution to serve as the countermeasure operation, and a set authority level set for a worker who may implement the solution; an solution memory section for authenticating the authority level of a worker who implements the countermeasure operation; and a solution notification section for separately reporting, when a problem event occurs, an executable solution corresponding to a set authority level equal to or less than the authority level, and an unexecutable solution corresponding to a set authority level exceeding the authority level.

A reinforcement learning method executed by a computer includes calculating a degree of risk for a state of a controlled object at a current time point with respect to a constraint condition related to the state of the controlled object, the degree of risk being calculated based on a predicted value of the state of the controlled object at a future time point, the predicted value being obtained from model information defining a relationship between the state of the controlled object and a control input to the controlled object; and determining the control input to the controlled object at the current time point, from a range defined according to the calculated degree of risk so that the range becomes narrower as the calculated degree of risk increases.

A machine learning apparatus able to obtaining an optimal shift amount of an assist gas. The machine learning apparatus comprises a state-observation section configured to observe machining condition data included in a machining program given to the laser machine, and measurement data of a dimension of dross generated at a cutting spot of the workpiece when the machining program is executed, as a state variable representing a current state of an environment in which the workpiece is cut; and a learning section configured to learn the shift amount in association with cutting quality of the workpiece, using the state variable.

An assistance apparatus includes a status information acquiring section that acquires a grinding condition as a status information, the grinding condition including set states associated with a plurality of movement command data, an evaluation result acquiring section that acquires evaluation results of a plurality of evaluation objects that are obtained under the grinding condition, a reward calculating section that calculates a reward for the status information based on the evaluation results, a policy storing section that stores a policy which is obtained from a value function, an action determining section that determines the movement command data to be adjusted and an adjustment amount at which said movement command data is adjusted, from among candidates of the plurality of movement command data that are adjustable, based on the status information and the policy, and an action information outputting section that is configured to output determined contents including an action information.

A computer implemented method for the maintenance optimization of a fleet or group of turbomachinery assets is disclosed. The method comprises the step of model training and setup, aiming at setting configurations parameters, that can be executed offline, and the step of online calculation on new input data, which is based on detected data and extracted statistical features. An anomaly identification and classification follow, thus calculating a risk assessment, for estimating the risk that an anomaly might cause any event that requires a maintenance task to be executed on one or more assets of the fleet.

A computer-implemented reinforcement learning method includes determining, based on a target probability of satisfaction of a constraint condition related to a state of a control object and a specific time within which a controller causes the state of the control object not satisfying the constraint condition to be the state of the control object satisfying the constraint condition, a parameter of a reinforcement learner that causes, in a specific probability, the state of the control object to satisfy the constraint condition at a first timing following a second timing at which the state of control object satisfies the constraint condition; and determining a control input to the control object by either the reinforcement learner or the controller, based on whether the state of the control object satisfies the constraint condition at a specific timing.

A machine learning device includes: a data extraction unit that extracts a first parameter and a second parameter from each of a plurality of machining programs for numerically controlling a machine tool, the first parameter being a parameter to be adjusted, the second parameter being a parameter to be used for adjusting the parameter to be adjusted; and a machine learning unit that learns a value of the first parameter according to a data set including the first parameter and the second parameter extracted by the data extraction unit.

A system and method for optimized industrial production using machine learning. The method includes creating a model defining dependencies among a plurality of parameters for an industrial production process, the plurality of parameters including a plurality of controlled parameters and a plurality of monitored parameters; training an agent via reinforcement learning based on iterative application of the model, wherein the agent is trained to determine new values for the plurality of controlled parameters based on current values of the plurality of monitored parameters in order to optimize the industrial production process with respect to at least one predetermined objective; and iteratively modifying, by the trained agent, current values of the plurality of controlled parameters in real-time during operation of the industrial production process.

A compressor controller for operating a compressor within an industrial automation environment is provided. The compressor controller includes a control module, configured to control the compressor via control settings, and a machine learning module, coupled with the control module. The machine learning module is configured to receive a set of supervised data related to the compressor, and to train with the supervised data to produce a Newtonian physics model representing the inputs and outputs of the compressor within the industrial automation environment. The machine learning module is also configured to receive performance data related to the compressor, receive environment data related to the compressor, and to process the performance data and environment data to produce predicted future performance data for the compressor, and to produce control settings for the compressor.

A control device includes a machine learning unit that performs machine learning of control for an operation of a control target device, an avoidance command value calculation unit that obtains an avoidance command value that is a control command value for the control target device, the control command value which satisfies constraint conditions including a condition for the control target device not to come into contact with an obstacle, and the control command value that an evaluation value obtained by applying the control command value to an evaluation function satisfies a prescribed end condition, and a device control unit that controls the control target device on the basis of the avoidance command value, in which a parameter value obtained through the machine learning in the machine learning unit is reflected in at least one of the evaluation function and the constraint condition.