A machining time estimating apparatus is stored with mechanical configuration-time data, which are control parameters relating to respective machining times of a plurality of numerically-controlled machine tools, and is provided with a machining time estimation unit, configured to estimate the machining time required for machining performed based on an NC command in a first one of the plurality of numerically-controlled machine tools, and a mechanical configuration difference time calculation unit configured to calculate machining times required for machining performed based on the NC command in the other ones of the plurality of numerically-controlled machine tools than the first numerically-controlled machine tool, based on the respective mechanical configuration-time data of the plurality of numerically-controlled machine tools.

Provided is a machining time prediction device including a predicted machining speed table where predicted machining speeds are registered in association with shape groups used for classification based on a shape of a machining path, a machining path generation unit generating machining path data including the machining path based on the program, a shape group determination unit determining which shape groups partial machining paths belong to, a path length addition unit adding and summarizing path lengths of the partial machining paths for the respective shape groups, a predicted machining time calculation unit calculating predicted machining times of the respective shape groups on the basis of a predicted machining speed table and the path lengths of the respective shape groups, a predicted machining time summation unit calculating a predicted machining time of the machining path by adding the predicted machining times of the respective shape groups, and a display unit displaying the predicted machining time of the machining path.

A numerical controller performs control for changing a tool mounted on a spindle to another tool stored in a tool magazine based on a machining program. The numerical controller analyzes a command by a block of the machining program, predicts a time required for machining by the analyzed command, and selects a tool changeable before a tool change command, during tool selection, based on the predicted time.

An NC machine tool is provided with a display device capable of displaying processing time individually for each function command of a block of an NC program. The display device of the NC machine tool is capable of displaying processing time for each function command. Thus, an operator is able to identify processing time for each function command via the display device.

To highly accurately predict remaining machining time required for cutting, a controller of a machining time prediction device includes a storage in which a machining program is stored, a simulator that performs a simulation in which a cutting machine cuts a workpiece in accordance with the machining program to generate a control pattern in which control information of a spindle and a holder is recorded, a machining time calculator that generates, based on the control pattern, a machining time table in which remaining machining time for each step of the machining program, a machining time acquirer that acquires a step of the machining program cutting of which is performed by the cutting machine at a current time point and acquires the remaining machining time for the step of the machining program, which has been acquired, from the machining time table, and a display controller that displays the remaining machining time that has been acquired by the machining time acquirer on a display screen.

A machine learning device of a finish-machining amount prediction apparatus observes, as state variables expressing a current state of an environment, finish-machining amount data indicating finish-machining amounts of the respective parts of a component and accuracy data indicating the accuracy of the respective parts of a machine, to which the component is attached. Then, the machine learning device acquires determination data indicating propriety determination results of the accuracy of the respective parts of the machine, to which the component after being subjected to finish machining is attached. After that, the machine learning device learns the finish-machining amounts of the respective parts of the component in association with the accuracy data by using the state variables and the determination data.

An automated method for discovering features in a repeatable process includes measuring raw time series data during the process using sensors. The time series data describes multiple parameters of the process. The method includes receiving, via a first controller, the time series data from the sensors, and stochastically generating candidate features from the raw time series data using a logic block or blocks of the first controller. The candidate features are predictive of a quality of a work piece manufactured via the repeatable process. The method also includes determining, via a genetic or evolutionary programming module, which generated candidate features are most predictive of the quality of the work piece, and executing a control action with respect to the repeatable process via a second controller using the most predictive candidate features. A system includes the controllers, the programming module, and the sensors.

A numerical controller estimates a machining continuable time before a currently controlled motor overheats if an output of the motor exceeds a continuous rated output and predicts respective execution times of command blocks and the machining continuable time for each command block, for a currently running block and its subsequent command blocks. Based on these predicted data, the numerical controller identifies a command block (alarm generation block) in which the motor overheats and a command block (stop block) in which driving control can be safely stopped, within the range of command blocks from the currently running command block to the alarm generation block.

Prediction of a machining time at higher accuracy considering a machine delay generated in a machine is allowed by a numerical controller of the invention. The numerical controller includes a reference machining time prediction unit for predicting a reference machining time corresponding to a machining time not considering a delay time of servo control and machine motion based on the machining program, a program analysis unit for extracting a combination of at least one program command included in the machining program, a data storage unit for storing information related to an actual delay time of servo control and machine motion measured for each combination of program command types, a correction time calculation unit for calculating a correction time for correction of the reference machining time based on the combination of the program commands extracted by the program analysis unit and the information stored in the data storage unit, and a machining time prediction unit for calculating a predicted machining time obtained by correcting the reference machining time using the correction time.

An automated method for discovering features in a repeatable process includes measuring raw time series data during the process using sensors. The time series data describes multiple parameters of the process. The method includes receiving, via a first controller, the time series data from the sensors, and stochastically generating candidate features from the raw time series data using a logic block or blocks of the first controller. The candidate features are predictive of a quality of a work piece manufactured via the repeatable process. The method also includes determining, via a genetic or evolutionary programming module, which generated candidate features are most predictive of the quality of the work piece, and executing a control action with respect to the repeatable process via a second controller using the most predictive candidate features. A system includes the controllers, the programming module, and the sensors.