Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, that optimize operation of manufacturing plants by adjusting the operation of manufacturing devices in manufacturing plants based on an assessment of their operations. Methods may include obtaining, from a first set of sensors, vibration data specifying vibration in a manufacturing device of a manufacturing plant. The vibration data may be processed to identify a vibration signature. Based on the vibration signature and known vibration signatures, a first operational state of the manufacturing device may be determined. One or more operational characteristics of the manufacturing device may be adjusted based on the first operational state of the manufacturing device, to achieve a second operational state.

A relearning necessity determination method is provided for determining a necessity of relearning of a learned diagnostic model in a machine tool including a machining abnormality diagnosing unit. The machining abnormality diagnosing unit determines normal or abnormality of machining using the diagnostic model generated through machine learning. The method includes storing a cumulative cutting time or a cumulative cutting distance of a tool mounted to the machine tool as a tool usage, storing the tool usage when the machining abnormality diagnosing unit diagnoses the machining as machining abnormality, and determining the necessity of the relearning of the diagnostic model based on a frequency distribution of the tool usage stored in the storing of the tool usage.

An abnormality factor identification apparatus includes a sensor signal obtaining unit that obtains sensor signals associated with the physical state of a machine, an operating state determination unit that determines operating states of the machine based on information obtained from the machine, an abnormality level calculation unit that calculates the abnormality levels of the sensor signals for each operating state of the machine determined by the operating state determination unit, and a factor identification unit that determines a factor in an abnormality in the machine from historical data being a series of the abnormality levels for each operating state.

A machine tool includes a first motor that receives load fluctuation when the workpiece is processed and a second motor that operates to change the plural kinds of tools. An information processing device takes out the current of the first motor measured by the first current sensor for each signal that occurs at the changing operation of the plural kinds of tools and is measured by the second current sensor, and relatively compares a non-negative function value that has a current value at each taken-out segment as a parameter for each number of times of processing on the workpiece, thereby detecting a tool abnormality for each kind of the tool.

To provide an arrangement capable of detecting spindle failure in a machine tool using an existing servo control device, without providing separate external sensors, a failure analysis device or the like. A servo control device (22), which detects failure of a spindle of a machine tool including the spindle, a feed shaft, and a positioning servomotor that is installed to the feed shaft and is for deciding the position of the spindle, includes: a feedback acquisition unit (222) that acquires a feedback signal of the positioning servomotor; and an analysis/detection unit 226 that analyzes the feedback signal acquired to detect failure of the spindle.

A management system including a network, plural manufacturing cells connected to the network, and a management device that is connected to the network and manages the plurality of manufacturing cells, in which the manufacturing cell includes: a machine tool; and a control device that controls the machine tool, analyzes a vibration state of a spindle positioning shaft of the machine tool, and sends an analysis result via the network; in which the management device includes: a communication unit that receives the analysis result sent by the control device; and a detection unit that compares the analysis results thus received, and compares vibration states of the machine tool of each of the manufacturing cells, so as to detect spindle failure of any of the machine tools; and in which the communication unit, in a case of the detection unit detecting the spindle failure, sends a failure signal via the network.

An abnormality factor identification apparatus includes a sensor signal obtaining unit that obtains sensor signals associated with the physical state of a machine, an operating state determination unit that determines operating states of the machine based on information obtained from the machine, an abnormality level calculation unit that calculates the abnormality levels of the sensor signals for each operating state of the machine determined by the operating state determination unit, and a factor identification unit that determines a factor in an abnormality in the machine from historical data being a series of the abnormality levels for each operating state.

Systems and techniques to facilitate tool failure analysis associated with fabrication processes are presented. A monitoring component determines a candidate tool failure associated with one or more fabrication tools based on sensor data generated by a set of sensors associated with the one or more fabrication tools. A signature component generates a signature dataset for the candidate tool failure based on data associated with the one or more fabrication tools. A comparison component compares the candidate tool failure to at least one previously determined tool failure based on the signature dataset and at least one other signature dataset associated with the at least one previously determined tool failure.

A diagnostic device includes a reception unit and a determination unit. The reception unit is configured to receive context information and sensing information. The context information corresponds to a certain operation of a target item that constitutes a target device. The context information is a piece of a plurality of pieces of context information each describing an operation of the target item determined depending on a type of operation of the target device. The sensing information is on a physical quantity that varies in accordance with the operation of the target item. The determination unit is configured to determine a state of the target item based on the sensing information detected while the target item is performing the certain operation, and based on a model corresponding to the received context information. The model is a model of one or more models respectively defined for one or more pieces of the context information.

A machining defect factor estimation device includes a machine learning device that learns an occurrence factor of a machined-surface defect based on an inspection result on a machined surface of a workpiece. The machine learning device observes the inspection result on the machined surface of the workpiece from an inspection device, as a state variable, acquires label data indicating the occurrence factor of the machined-surface defect, and learns the state variable and the label data in a manner such that they are correlated each other.