Provided is an information processing device, etc., that provides information which is the basis for quick detection of abnormalities that occur in a device. An information processing device calculates a degree of suitability between observation information and prediction information, the observation information observed for a system suffering an effect from an certain device, the prediction information predicted in accordance with a model for a state of the system; and calculates a difference between manipulation amount to the certain device and predictive manipulation amount predicted for the manipulation amount based on the model, the difference being a difference in case that the degree satisfies a predetermined calculation condition.

An information processing method includes: calculating a probability density distribution of a work time that is at least part of a setup time, based on production performance data read from storage, the setup time being time taken for a setup work that is performed between lots; determining whether the work time is anormal, based on the probability density distribution; and outputting a result of the determining.

An abnormality determination device includes a control unit for determining an abnormality of a robot, the control unit being configured to calculate a measurement probability distribution which is a probability distribution using disturbance torque acquired during a predetermined period as a random variable. The control unit causes an average of the calculated measurement probability distribution to conform to an average of an evaluation normal model which is a predetermined probability distribution, compares the measurement probability distribution with the evaluation normal model of which the respective averages conform to each other, and determines an abnormality of the robot in accordance with a result of the comparison.

A programmable manufacturing advisor includes an information unit that receives measurements for at least one parameter of each operation of a plurality of operations in the manufacturing process, and an analytics unit that determines a baseline performance metric for the manufacturing process based on the measurements of the at least one parameter. The programmable manufacturing advisor also includes an optimization unit that determines a recommended improvement action by determining a predicted performance metric for the manufacturing process based on an adjusted value of the at least one parameter and comparing the predicted performance metric to the baseline performance metric. The optimization unit also automatically presents the recommended improvement action to the operations manager.

A programmable manufacturing advisor includes an information unit that receives measurements for at least one parameter of each operation of a plurality of operations in the manufacturing process, and an analytics unit that determines a baseline performance metric for the manufacturing process based on the measurements of the at least one parameter. The programmable manufacturing advisor also includes an optimization unit that determines a recommended improvement action by determining a predicted performance metric for the manufacturing process based on an adjusted value of the at least one parameter and comparing the predicted performance metric to the baseline performance metric. The optimization unit also automatically presents the recommended improvement action to the operations manager.

A method for detecting a fault in a robot joint includes the steps of: performing a first torque measurement at the robot joint to thereby obtain a first set of torque values; calculating a first distribution characteristic reflecting a distribution of the first set of torque values; performing a second torque measurement at the robot joint to thereby obtain a second set of torque values; calculating a second distribution characteristic reflecting a distribution of the second set of torque values; and comparing the first and the second distribution characteristics to determine whether a fault is present or not. A difference in the distributions of torque measurements is a robust fault indicator that makes use of the repetitive behavior of the system.

Provided is an information processing device, etc., that provides information which is the basis for quick detection of abnormalities that occur in a device. An information processing device calculates a degree of suitability between observation information and prediction information, the observation information observed for a system suffering an effect from an certain device, the prediction information predicted in accordance with a model for a state of the system; and calculates a difference between manipulation amount to the certain device and predictive manipulation amount predicted for the manipulation amount based on the model, the difference being a difference in case that the degree satisfies a predetermined calculation condition.

A method for analyzing variation causes of manufacturing process is applied. The method includes acquiring manufacturing process data of a plurality of products, and using at least one of a non-probability based classifier and a probability based classifier to compute manufacturing process data to acquire a contribution rate of each of the manufacturing process parameters. The method further includes determining whether a classifier accuracy rate is greater than a threshold. The method further includes, if yes, performing a deleting operation to delete a manufacturing process parameter having a lowest contribution rate and using the at least one of the non-probability based classifier and the probability based classifier to compute the manufacturing process data again; and if no, setting the manufacturing process parameters not deleted by the deleting operation plus the manufacturing process parameter deleted in the last deleting operation as the at least one crucial manufacturing process parameter.