A camera photographs a part to be estimated, which is produced by cutting a sheet metal in advance, and a dimension reference marker. An image processing unit generates edge data by extracting an edge of the part photographed by the camera, and enlarges or reduces the edge data based on a size of the dimension reference marker photographed by the camera such that a size of the edge corresponds to an actual size of the part. A machining time calculation unit calculates a length of a cutting line for cutting out the part from the sheet metal based on the edge of the edge data corresponding to the actual size of the part, and calculates a machining time for producing the part by cutting the cutting line in accordance with a material and a thickness of the sheet metal.

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.

A machine learning device included in a tool selecting apparatus includes a state observing unit that observes, as state variables indicative of a current environmental state, data related to machining condition, data related to cutting condition, data related to machining result, and data related to a tool, and a learning unit that, by using the state variables, learns distribution of the data related to the machining condition, the data related to the cutting condition, and the data related to the machining result, with respect to data related to the tool.

In a facility operation analysis device configured to continuously grasp the extent of change (the amount of change) over time of actuators constituting a manufacturing facility, when displaying a result of evaluation on a display device, an evaluating portion compares a measured amount of change with thresholds of the amount of change that are set within a normal range where the manufacturing facility is not stopped, and displays the result of evaluation in which the measured amount of change is ranked.

A machining program editing device calculates an editable time for a block of a machining program, makes editable only those of a plurality of blocks in the machining program which have the editable time left remaining, and locally writes only edited portions into a machining program used for control.

A device configured to predict an execution time of an auxiliary function for tool change extracts an auxiliary function command for tool change from a machining program, calculates the storage position of a before-exchange tool and the storage position of an after-exchange tool, based on the auxiliary function command, and calculates a distance between tools, based on the results of the calculation. Also, the prediction device predicts the execution time of the auxiliary function command for tool change with reference to a database in which the distance between tools is associated with an actual value of the auxiliary function execution time for tool change.

The present invention indicates an information processing system that can be exploited in a large number of manufacturing companies, which work on order.

In such companies, the experience of the workers is a strategic and essential resource; the present invention transforms the substance of such experience, from a purely humanistic entity into a technical factor in all respects: a heritage preserved in the memories of computer systems. The invention consists in teaching the use of known mathematical tools derived from identification theory, to extract and encode the aforementioned wealth of experience. The inventive step consists in the fact that, although the necessary data and information are potentially available, a sample of training data, as such, suitable for using an identification model, is in fact not available, nor it is trivial to derive it from the data that are actually available.

A machining condition search device according to the disclosure includes a machining condition generation unit, a practical machining command unit, a machining evaluation unit, a prediction unit, an optimum machining condition calculation unit. The machining condition generation unit generates a machining condition defined by one or more control parameters settable on a machining apparatus. The practical machining command unit causes the machining apparatus to perform machining based on a generated machining condition. The machining evaluation unit generates an evaluation value of performed machining, on the basis of information indicating a machining result of the performed machining. The prediction unit predicts an evaluation value corresponding to a machining condition under which machining is not performed, on the basis of the evaluation value and the machining condition corresponding to the evaluation value. The optimum machining condition calculation unit obtains an optimum machining condition on the basis of a prediction value predicted by the prediction unit and an evaluation value generated by the machining evaluation unit. The optimum machining condition is a machining condition under which an evaluation value is equal to or greater than a threshold and a tolerance is maximum.

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.

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.