Fanuc Corporation

Kazuhiro Satou

Kazunori Iijima

Yohei Kamiya

Yoshitaka Kubo

Liancheng Hu

Hiroyasu Asaoka

Keita Hada

Chao Zhi

Keitarou Inagaki

Takeshi Sumi

Ryutaro Ishikawa

This abnormality detection device: causes a motor that drives a drive unit at a plurality of rotational speeds to perform a detection operation based on a command for diagnosing the state of the drive unit, acquires, as information indicating the operating state of the drive unit, a control command for the motor driving the drive unit or a feedback signal from the motor driving the drive unit, during the detection operation; analyzes the control instruction for the motor driving the drive unit or the feedback signal from the motor; determines the state of the drive unit based on the result of the analysis, and notifies, based on the determination result, that the state of the drive unit is different from that in normal time.

Abnormality detection device

A diagnostic device is a device for estimating the tension of a belt of an industrial machine for transmitting power, and is provided with a control unit configured to control a diagnostic operation in which the belt is driven, a data acquisition unit configured to acquire at least feedback data at the time of the diagnostic operation, a preprocessing unit configured to analyze frequency-gain characteristics of the feedback data and create, as input data, a range including a resonant frequency and an anti-resonant frequency in the characteristics, and a machine learning device configured to perform processing related to machine learning, based on the data created by the preprocessing unit. The diagnostic device supports inference or abnormality detection of the value of the belt tension.

Diagnostic device and machine learning device

A diagnostic apparatus of the invention acquires normal data related to an operating state during normal operation of an industrial machine, stores the normal data, generates a learning model by learning based on the stored normal data, and performs an estimation process for normality or abnormality of an operation of the industrial machine using the learning model. The diagnostic apparatus of the invention further generates verification data including at least one piece of abnormal data based on the stored normal data to verify validity of the learning model on receiving a result of the estimation process using the learning model based on the verification data.

Diagnostic apparatus for generating verification data including at least one piece of abnormal data based on normal data

To provide an abnormality monitoring device capable of reducing the size of a mounted device, enabling high-speed response, and achieving high accuracy in detecting abnormality. The abnormality monitoring device includes: at least one filter that extracts state information pertaining to drive of a mechanism of an industrial machine using a motor, as a signal of at least one frequency band; an integrator that integrates an output of the filter in each frequency band; and an abnormality detection unit that detects abnormality based on an integrated value integrated by the integrator. The state information may be control information of the controller that controls the motor or detection information from at least one detector attached to the mechanism.

Abnormality monitoring device, abnormality monitoring method, and control device

A plurality of learning models generated by performing machine learning on physical quantities observed during respective operations of a plurality of machines are stored in advance. Then, using the stored learning models and a physical quantity observed during an operation of a machine which is an object to be diagnosed, characteristic differences between the machine which is the object to be diagnosed and the plurality of respective machines are calculated, a learning model used in a diagnosis of the operation of the machine which is the object to be diagnosed is selected based on the calculated characteristic differences, and the operation of the machine which is an object to be diagnosed using the selected learning model is diagnosed.

Diagnosis apparatus and diagnosis method

The data management device capable of calculating an evaluation index based on the sensor data includes: a sensor data acquisition unit that acquires the sensor data from one or more sensors installed in an industrial machine; an evaluation index calculation unit that calculates the evaluation index with use of the sensor data; a sensor data storage unit that saves the sensor data; and a sensor data deletion unit that deletes the sensor data when a total volume of the sensor data in the sensor data storage unit exceeds an upper limit. The sensor data deletion unit determines saving priority of the sensor data based on a degree of change in the evaluation index and deletes the sensor data in accordance with the saving priority.

Data management device, data management program, and data management method

A diagnostic apparatus acquires data relating to a state of a machine, performs preprocessing on the acquired data, and modifies the preprocessed data by using a statistic relating to the state of the machine. Then, the diagnostic apparatus performs a process of machine learning by an auto encoder on the basis of the modified data and learns or diagnoses the state of the machine. Thus, this diagnostic apparatus provides a learning and inference method capable of uniformly handling a scale of data indicating a feature.

Diagnostic apparatus

A numerical control system detects a state amount indicating an operation state of a machine tool, creates a characteristic amount that characterizes the state of a machining operation from the detected state amount, infers an evaluation value of the operation state of the machine tool from the characteristic amount, and detects an abnormality in the operation state of the machine tool on the basis of the inferred evaluation value. The numerical control system generates and updates a learning model by machine learning that uses the characteristic amount, and stores the learning model in correlation with a combination of conditions of the machining operation of the machine tool.

Numerical control system that detects an abnormality in an operation state

A numerical control system detects a state amount indicating a state of machining operation of a machine tool, creates a characteristic amount that characterizes the state of machining operation from the detected state amount, infers an evaluation value of the state of machining operation from the characteristic amount, and detects an abnormality in the state of machining operation on the basis of the inferred evaluation value. The numerical control system generates and updates a learning model by machine learning that uses the characteristic amount, and stores the learning model in correlation with a combination of conditions of the machining operation of the machine tool.

Numerical control system

A collision position estimation device allowing extraction of data related to a torque of a section related to collision of a cushion member includes a machine learning device. The machine learning device includes a state observation unit for observing axis movement data indicating information related to movement of the axis and motor torque data indicating data related to torque of a motor driving the axis as a state variable representing a current state of an environment, a label data acquisition unit for acquiring collision position data indicating the position of the axis during collision of the cushion member as label data, and a learning unit for associating and learning the information related to movement of the axis and the data related to the torque of the motor driving the axis with the position of the axis during collision of the cushion member using the state variable and the label data.

Collision position estimation device and machine learning device

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.

Abnormally factor identification apparatus

A sensor device includes a plurality of systems each having a sensor element, and a computation unit configured to calculate as a first value a value of at least one of a force and a moment applied to a detection target in a predetermined axial direction, based on a detection signal detected by the sensor element, and an abnormality determining unit configured to compare the first values calculated by the computation units of the systems with one another, and determine that there is an abnormality if a difference of the first value is greater than or equal to a predetermined amount. The computation unit of at least one of the systems calculates as a second value a value of at least one of a force and a moment applied to the detection target in the axial direction, based on detection signals detected by the sensor elements of the systems.

Sensor device

A controller can switch a control system of a motor to a diagnostic operation mode in addition to a normal operation mode. Abnormality of the motor can be detected by taking advantage of the appearance of a clear difference between a feedback value detected when the motor is normal and a feedback value detected when the motor is abnormal if the control system is switched to the diagnostic mode.

Controller

Upon performing diagnosis of a machine tool, etc., data suited to diagnosis is acquired while also reducing the burden on the user. A diagnostic data acquisition system that acquires diagnostic data for diagnosing a machine tool includes: a control unit that controls driving of a mobile part of the machine tool based on control data; a timing generation unit that generates an acquisition timing for the diagnostic data based on the control data; and a diagnostic data acquisition unit that acquires data which varies accompanying driving of the mobile part according to control by the control unit, as the diagnostic data.

Diagnostic data acquisition system, diagnostic system, and computer readable medium

In a case of sending characteristic data representing a characteristic of measurement data, rather than the measurement data itself from a sensor, characteristic data suited to the connected sensor is sent. A sensor interface device () which is connected in a communication path between a measurement means () and a higher-order device (), includes: a data acquisition means () for acquiring measurement data, which is data based on a physical quantity measured by the measurement means (); a storage means () for storing the measurement data thus acquired; a learning means () for performing machine learning with a measurement data group stored by the storage means () as an input, thereby performing extraction of characteristic data, which is data representing a characteristic of the measurement data group; and a communication means () for sending the characteristic data extracted by the learning means () to the higher-order device ().

Sensor interface device, measurement information communication system, measurement information communication method, and non-transitory computer readable medium

Growing community of inventors

Yamanashi, Japan

Kazuhiro Satou