Provided is an abnormality detection device with which an abnormality of a machining state of a machine tool can be detected based on information on a section where machining is actually performed in machine tool-based machining. The abnormality detection device detects an abnormality of a machining state of a machine tool machining a workpiece with a tool. The machine tool includes a determination unit determining the machining state by using information related to an actual cutting section in the tool-based machining of the workpiece in the machine tool. The determination unit performs the machining state determination by using a deviation in position and length of a section recognized as the actual cutting section and a physical quantity in the actual cutting section acquired from the machine tool.

A method, system and computer-usable medium are disclosed for monitoring and controlling a machining process of parts. Data as to dimensions of produced parts are gathered during a production process. The parts are produced based on part control plan. The data of the dimensions are plotted as to statistical information related to a distribution curve. Determination is made if a trend in the dimensional data approaches an upper control limit and a lower control limit. Corrective action is taken if the trend approaches either the upper control limit or the lower control limit.

A method is provided for assessing wear of a drill bit throughout its use for carrying out the drilling of elements to be drilled constituted by at least one layer and at least one material. The wear of the drill bit expresses its capacity to perform a drilling that meets at least one criterion of quality of a drilling. The method includes at least: measuring or detecting at least one parameter having an effect on the wear of the drill bit, the parameter being chosen from: the depth of drilling performed by the drill bit, and the entry of the drill bit into the element to be drilled; and determining at least one state of wear of the drill bit, each state of wear being determined as a function of one of the parameters and being characteristic of one of the criteria of quality of a drilling.

A self-aware machine platform is implemented through analyzing operational data of machining tools to achieve machine tool damage assessment, prediction and planning in manufacturing shop floor. Machining processes are first identified by matching similar processes through an ICP algorithm. Machining processes are further clustered by Hotelling's T-squared statistics. Degradation of the machining tool is detected through a trend of the operational data within a cluster of machining processes by a monotonicity test, and the remaining useful life of the machining tool is predicted through a particle filter by extrapolating the trend under a first-order Markov process. In addition, process anomalies across machines are detected through a combination of outlier detection methods including SOMs, multivariate regression, and robust Mahalanobis distance. Warnings and recommendations are flexibly provided to manufacturing shop floor based on policy choice.

Information is collected from a management target device having a drive unit such as a machine tool, and this collected information is more practically used. An information collection device includes a collection unit that collects, from management target devices having a drive unit, operating state information which is information indicating an operating state of the management target device while operating accompanying movement of the drive unit; and a comparison unit that extracts a plurality of sets of information matching in a predetermined condition from the operating state information thus collected, and outputs a comparison result of the plurality of sets of information thus extracted.

A self-aware machine platform is implemented through analyzing operational data of machining tools to achieve machine tool damage assessment, prediction and planning in manufacturing shop floor. Machining processes are first identified by matching similar processes through an ICP algorithm. Machining processes are further clustered by Hotelling's T-squared statistics. Degradation of the machining tool is detected through a trend of the operational data within a cluster of machining processes by a monotonicity test, and the remaining useful life of the machining tool is predicted through a particle filter by extrapolating the trend under a first-order Markov process. In addition, process anomalies across machines are detected through a combination of outlier detection methods including SOMs, multivariate regression, and robust Mahalanobis distance. Warnings and recommendations are flexibly provided to manufacturing shop floor based on policy choice.

Information is collected from a management target device having a drive unit such as a machine tool, and this collected information is more practically used. An information collection device includes a collection unit that collects, from management target devices having a drive unit, operating state information which is information indicating an operating state of the management target device while operating accompanying movement of the drive unit; and a comparison unit that extracts a plurality of sets of information matching in a predetermined condition from the operating state information thus collected, and outputs a comparison result of the plurality of sets of information thus extracted.

The numerical control system includes: detecting circuitry to obtain cutting force generated in a machine tool; controlling circuitry to calculate a control amount according to a cutting condition and to control a feed drive mechanism of the machine tool; countermeasure determining circuitry to, when it is detected from the cutting force or a state of the feed drive mechanism of the machine tool that a machining defect has occurred, calculate a plurality of deviation degrees for possible causes of the machining defect, and compare the calculated deviation degrees and to thereby determine a cause of the machining defect whose occurrence has been detected; and correction-amount calculating circuitry to calculate, according to the cause of the machining defect determined by the countermeasure determining circuitry, a correction amount with respect to the control amount, and then output the correction amount to the controlling circuitry.

A control system for evaluating residual operating life of a machine component of a machine tool includes a sensor and a control system. The sensor is disposed on the machine tool and is configured to sense movement of the machine component. The control device is configured to calculate a length of time based on a sense signal received from the sensor and sampled at a time point right after the machine component is freshly oiled, and to enable output of an alarm when determining that the length of time thus calculated is smaller than a predetermined length.

The numerical controller creates a machining path on which a wire electrode is moved by analyzing blocks of a machining program, and creates interpolation data indicating an amount of movement for each interpolation period on the machining path. Further, the numerical controller calculates a length of the wire electrode used for machining (machined surface length) for each interpolation period, calculates a consumption amount of the wire electrode for each interpolation period, calculates a compensation amount for compensating the amount of movement based on the interpolation data, on the basis of the calculated consumption amount and compensates the amount of movement indicated by the interpolation data, based on the calculated compensation amount.