Feed rate scheduling methods include measuring a topography of a grinding wheel of a machine tool, calculating a topography parameter using the topography, and calculating a feed rate scheduling parameter for a toolpath of the grinding wheel based on the topography parameter. The topography may be measured using microscopy. The topography parameter may include a plurality of parameters including a density of crystals at a given depth (C(h)) of the grinding wheel and/or an area fraction of crystals protruding at a given depth (α(h)) of the grinding wheel. The feed rate scheduling parameter may include a grinding wheel feed rate, a grinding wheel spin rate, and/or a grinding wheel cutting depth, among other parameters.

A machine learning device acquires from a numerical controller information relating to machining when the machining is performed, and further acquires an actual delay time due to servo control and due to machine movement which are caused in the machining when the machining is performed. Then, the device performs supervised learning using the acquired machining-related information as input data, and using the acquired actual delay time due to servo control and due to machine movement as supervised data, and constructs a learning model, thereby predicting the machine delay time caused in a machine with high precision.

A method for compensating for the deflection of a milling cutter during the machining of a workpiece by a numerically controlled machine tool having a plurality of axes includes: executing a learning cut on a test workpiece having a known geometry by the milling cutter mounted on a tool spindle in a climb milling mode, and in doing so, ascertaining a correlation between a quantity that is proportional to the torque of the drive of the tool spindle and the deflection of the milling cutter normal to a surface of the test workpiece, the deflection being determined by comparing the actual contour of the test workpiece to a setpoint contour. This is followed by storing of the correlation for the milling cutter and machining of the workpiece by the milling cutter in a climb milling mode, while utilizing the stored correlation for compensating for the deflection of the milling cutter by applying a positional correction that is proportional to the quantity to a setpoint position of the axes of the machine tool.

A computer-implemented method for detecting faults and events related to a system includes receiving sensor data from a plurality of sensors associated with the system. A hierarchical failure model of the system is constructed using (i) the sensor data, (ii) fault detector data, (iii) prior knowledge about system variables and states, and (iii) one or more statistical descriptions of the system. The failure model comprises a plurality of diagnostic variables related to the system and their relationships. Probabilistic reasoning is performed for diagnostic or prognostic purposes on the system using the failure model to derive knowledge related to potential or actual system failures.

A non-transitory computer-readable recording medium records an estimation program causing a computer to execute processing which includes: calculating a reconfiguration error from an input result value and a reconfiguration value that is estimated by a first estimator, which estimates a parameter value from a result value learned on a basis of past data, and a second estimator, which estimates a result value from a parameter value, by using a specific result value or a neighborhood result value in a neighborhood of the specific result value; searching for a first result value that minimizes a sum of a substitute error that is calculated from the input result value and the specific result value and the reconfiguration error; and outputting a parameter value that is estimated from the first result value by using the first estimator.

A computer-implemented method for detecting faults and events related to a system includes receiving sensor data from a plurality of sensors associated with the system. A hierarchical failure model of the system is constructed using (i) the sensor data, (ii) fault detector data, (iii) prior knowledge about system variables and states, and (iii) one or more statistical descriptions of the system. The failure model comprises a plurality of diagnostic variables related to the system and their relationships. Probabilistic reasoning is performed for diagnostic or prognostic purposes on the system using the failure model to derive knowledge related to potential or actual system failures.

A method for controlling and adjusting a machining parameter of a processing machine detects and acquires information of workpieces during processing, and calculates an error compensation depending on the detected information and a mathematical model. The error compensation is compared with a first preset value and a determination made as to whether the error compensation is greater than a first preset value. The machining parameter is adjusted when the error compensation is not greater than the first preset value, the processing machine can be stopped if greater. An apparatus, and a non-transitory computer readable medium for controlling the machining parameter are also disclosed.

A method for compensating for the deflection of a milling cutter during the machining of a workpiece by a numerically controlled machine tool having a plurality of axes includes: executing a learning cut on a test workpiece having a known geometry by the milling cutter mounted on a tool spindle in a climb milling mode, and in doing so, ascertaining a correlation between a quantity that is proportional to the torque of the drive of the tool spindle and the deflection of the milling cutter normal to a surface of the test workpiece, the deflection being determined by comparing the actual contour of the test workpiece to a setpoint contour. This is followed by storing of the correlation for the milling cutter and machining of the workpiece by the milling cutter in a climb milling mode, while utilizing the stored correlation for compensating for the deflection of the milling cutter by applying a positional correction that is proportional to the quantity to a setpoint position of the axes of the machine tool.

A machine learning device acquires from a numerical controller information relating to machining when the machining is performed, and further acquires an actual delay time due to servo control and due to machine movement which are caused in the machining when the machining is performed. Then, the device performs supervised learning using the acquired machining-related information as input data, and using the acquired actual delay time due to servo control and due to machine movement as supervised data, and constructs a learning model, thereby predicting the machine delay time caused in a machine with high precision.

A method for providing dynamic state information for a coordinate measuring machine that includes a base, a probe head, a machine structure linking the probe head to the base and a drive mechanism that moves the probe head. A dynamic model with first state variables represents an actual state of physical properties of the coordinate measuring machine. The first state variables are provided in a database and the actual state of the coordinate measuring machine is determined using the dynamic model. The state variables are monitored and, based thereon, the change of the state variables is determined. Updated, second state variables are set regarding the determined change of the first state variables. The dynamic model is updated using the second state variables in place of the first state variables, wherein the actual state of the coordinate measuring machine is calculated based on the second state variables.