A failure diagnostic device includes a torque detector that detects disturbance torques applied to joint shafts included in a multi-axis robot, a torque grouping circuit that groups the disturbance torques according to a content of an operation executed by the multi-axis robot upon detection of each disturbance torque, a torque correction circuit that obtains a corrected disturbance torque standardized between a plurality of operations with different contents based on a representative value preliminarily set for each grouped disturbance torque and the disturbance torque detected by the torque detector, and a failure diagnostic circuit that performs a failure diagnosis on the multi-axis robot by comparing the corrected disturbance torque with a threshold.

An apparatus, method, and non-transitory machine-readable medium provide for improved feature extraction and fault detection in a non-stationary process through unsupervised machine learning. The apparatus includes a memory and a processor operably connected to the memory. The processor receives training data regarding a field device in an industrial process control and automation system; extracts a meaningful feature from the training data; performs an unsupervised classification to determine a health index for the meaningful feature; identifies a faulty condition of real-time data using the health index of the meaningful feature; and performs a rectifying operation in the industrial process control and automation system for correcting the faulty condition of the field device.

A method for determining a status of one of multiple machine components of a machine on the basis of a digital machine model, wherein the digital machine model describes the multiple machine components, includes the steps of: determining component manufacturer data of the multiple machine components; determining machine manufacturer data of the multiple machine components; determining machine operator data of the multiple machine components; and determining the status of the one of the multiple machine components by linking the determined component manufacturer data, the determined machine manufacturer data and the determined machine operator data.

A method for determining a status of one of multiple machine components of a machine on the basis of a digital machine model, wherein the digital machine model describes the multiple machine components, includes the steps of: determining component manufacturer data of the multiple machine components; determining machine manufacturer data of the multiple machine components; determining machine operator data of the multiple machine components; and determining the status of the one of the multiple machine components by linking the determined component manufacturer data, the determined machine manufacturer data and the determined machine operator data.

A device for monitoring an operating condition of a machine is disclosed. The device includes a sound detection device located in proximity to the machine and configured to collect a plurality of sound signals in real-time from the machine. The device also includes a processor electrically coupled to the sound detection device. The processor is configured to acquire one or more predefined sound analytics models associated with the machine. The processor is also configured to analyse the plurality of sound signals based on the one or more predefined sound analytics models. The processor is further configured to identify the operating condition of the machine based on an analysed result and the one or more predefined sound analytics models. The device also includes a sound analytics system which is further configured to update the one or more predefined sound analytics models based on the plurality of sound signals.

A control system of a machine tool includes an analysis device, the analysis device includes acquisition portions which acquire chronological control data when a work is machined and which acquire spatial machined surface measurement data after the machining of the work, a storage portion which stores the control data and the machined surface measurement data, a data-associating processing portion which associates the control data and the machined surface measurement data with each other in two machining directions, a machined surface failure detection portion which detects a failure on the machined surface of the work and a location thereof based on the machined surface measurement data in the two machining directions and an identification portion which identifies a drive axis that causes the failure from the detected failure and the machining direction of the control data corresponding to the detected failure location.

An apparatus, method, and non-transitory machine-readable medium provide for improved feature extraction and fault detection in a non-stationary process through unsupervised machine learning. The apparatus includes a memory and a processor operably connected to the memory. The processor receives training data regarding a field device in an industrial process control and automation system; extracts a meaningful feature from the training data; performs an unsupervised classification to determine a health index for the meaningful feature; identifies a faulty condition of real-time data using the health index of the meaningful feature; and performs a rectifying operation in the industrial process control and automation system for correcting the faulty condition of the field device.

An evaluation apparatus includes a storage unit that stores a model modeling a state of a facility provided in a plant, a simulator that adjusts a parameter that is set in the model so that a difference between an actual measurement value based on a process value of the facility in a first state and a first simulate value calculated by using the model is equal to or less than a threshold, and an estimation unit that estimates a first estimated operating point that indicates an operation state of the facility in the first state based on the adjusted parameter.

A framework for autonomous predictive health monitoring includes online monitoring, offline training, and self-learning components. The monitoring component includes analyzing streaming incoming process data, which includes process variable and key performance indicators (KPIs), from multiple sources, in real time, to determine an overall health index, determine faults, diagnose and isolate faulty process variables that contribute to the health index, and predict a trend and a magnitude of the health index before failure. The self-learning component includes services linked to event management, to correct the health index from probabilities calculated based on operator feedback on true or false events after analyzing each of the detected events, self-tune limits and other model parameters, and trigger training of a model when a new normal pattern is detected. The offline training component creates models to classify each of the moving data window, cluster training windows, remove duplicate windows, and minimize training data storage size.

In a component mounting system, recovery processing is repeated until a recovery count number Nr is larger than or equal to a defined count number Nth in a case where a pickup defect of a component occurs, an elapsed time is measured from error stoppage of a component mounting machine to canceling of the error stoppage in which the component mounting machine is error-stopped when the recovery count number Nr is larger than or equal to the defined count number Nth, the defined count number Nth is increased within a range in which the defined count number does not exceed the upper limit value Nmax in a case where the elapsed time is shorter than a defined time Tth, and the defined count number Nth returns to an initial value in a case where the elapsed time is longer than or equal to the defined time Tth.