A controller for controlling a plurality of robots includes a failure prediction section configured to predict a failure time for each of the robots; and a load adjustment section configured to perform adjustment of a work load of each of the robots according to each of the predicted failure times, so that each of the robots operates until a maintenance time determined in common to each of the robots.

A controller for controlling a plurality of robots includes a failure prediction section configured to predict a failure time for each of the robots; and a load adjustment section configured to perform adjustment of a work load of each of the robots according to each of the predicted failure times, so that each of the robots operates until a maintenance time determined in common to each of the robots.

A machine learning device included in a life predicting device observes, as a state variable, life related data related to a life of a consumable component, creates a probability model of a service life for replacement of the consumable component on the basis of the life related data, and predicts, using the created probability model, the service life for replacement of the consumable component based on the life related data.

A cell control apparatus comprises an operation information acquisition unit which acquires operation information of manufacturing machine, a failure prediction unit which predicts a failure time of the manufacturing machine based on the operation information of the manufacturing machine, and a replacement time acquisition unit which acquires a replacement time of the component from a component management apparatus. When the failure time is earlier than the replacement time, the cell control apparatus performs a control for reducing an operation load of the manufacturing machine on which a failure of the component is predicted so that the failure time is later than the replacement time.

A system and method for unsupervised prediction of machine failures. The method includes monitoring sensory inputs related to at least one machine; analyzing, via at least unsupervised machine learning, the monitored sensory inputs, wherein the output of the unsupervised machine learning includes at least one indicator; identifying, based on the at least one indicator, at least one pattern; and determining, based on the at least one pattern and the monitored sensory inputs, at least one machine failure prediction.

Systems, methods, non-transitory computer readable media can be configured to accessing a target sensor log corresponding to a first machine; accessing one or more prior sensor logs corresponding to the first machine and one or more prior sensor logs corresponding to a plurality of second machines which are of the same type as the first machine; accessing a plurality of computer readable logs corresponding to the first machine and the second machines, the computer readable logs for each second machine comprising a maintenance log comprising a plurality of maintenance task objects, each maintenance task object comprising a time and a maintenance task type; determining a set of statistical metrics characterising a difference between the target sensor log and each prior sensor log; selecting a sub-set of the prior sensor logs in dependence upon the statistical metrics; analysing the maintenance logs to correlate each prior sensor log included in the subset to one or more correlated maintenance tasks; selecting a priority maintenance task based on the sub-set of prior sensor logs, t and the correlated maintenance tasks; and outputting the priority maintenance task.

A cell control system that reduces an abnormality occurrence probability in a manufacturing cell according to a manufacturing cell operation plan includes a cell controller that transmits an operation instruction to a manufacturing machine of the manufacturing cell. The cell controller includes a machine operation instructing unit that transmits the operation instruction to each manufacturing machine based on an operation schedule, an operation information collecting unit that collects operation information of the manufacturing machine, an alarm probability estimating unit that estimates an alarm occurrence probability of the manufacturing machine, a schedule candidate creating unit that creates at least one operation schedule candidate having a changed order of an operation element of the operation schedule or start time, and an optimal candidate selecting unit that selects a shortest necessary time that takes the alarm occurrence into account from the operation schedule and the operation schedule candidate as a selected operation schedule.

A data collecting processing part of a machine tool collects data indicating a state of a component at any time and sends the data. A maintenance timing prediction device has a collection data storing part that stores the data, a component replacement history storing part that stores a replacement history of the component, and a component lifetime prediction processing part that predicts a lifetime as the next replacement timing of the component. The component lifetime prediction processing part extracts data indicating a similar trend at the past replacement date of the component by referring to the component replacement history storing part and the collection data storing part, and predicts a threshold as data at the next replacement timing based on the latest replacement date of the component and the trend according to the extracted data, and predicts the lifetime based on the threshold.

A cell control apparatus comprises an operation information acquisition unit which acquires operation information of manufacturing machine, a failure prediction unit which predicts a failure time of the manufacturing machine based on the operation information of the manufacturing machine, and a replacement time acquisition unit which acquires a replacement time of the component from a component management apparatus. When the failure time is earlier than the replacement time, the cell control apparatus performs a control for reducing an operation load of the manufacturing machine on which a failure of the component is predicted so that the failure time is later than the replacement time.

A system and method for unsupervised prediction of machine failures. The method includes monitoring sensory inputs related to at least one machine; analyzing, via at least unsupervised machine learning, the monitored sensory inputs, wherein the output of the unsupervised machine learning includes at least one indicator; identifying, based on the at least one indicator, at least one pattern; and determining, based on the at least one pattern and the monitored sensory inputs, at least one machine failure prediction.