A method and system utilizing multi-sensor analysis and data point correlation is provided for predictive monitoring and maintenance of a pressurized fluid cutting system. In a disclosed aspect, multiple sensed characteristics of system operation are correlated to determine a particular failure mode. Identification of the failure mode through active sensor data analysis and correlation facilitates predictive maintenance, minimizes system downtime, and optimizes system output.

A system includes a computer numerical control (CNC) machining system configured to perform a machining operation to define a feature on a workpiece and a machine edge controller disposed external of the machining system and in communication with the CNC machine system. The machine edge controller is configured to perform a machining evaluation during the machining operation. In executing the machining evaluation, the machine edge controller is configured to acquire data indicative of characteristics of the CNC machining system during the machining operation and compare the data with one or more machining baseline parameters associated with the machining operation to determine an abnormal operation of the CNC machining system. The one or more machining baseline parameters define a nominal response of the CNC machining system for performing the machining operation.

An operator defines a process, such as a process for the manufacturing of a product, using templates that may be edited graphically. Each process includes a set of steps that a user must perform in order to accomplish the process. Each step in the process may be associated with one or more pieces of machinery on the floor to achieve the execution of the process, either in advance or at execution time. Each step may also provide various forms of instruction, monitoring, and feedback to aid the user of the associated machinery in performing the process. Data may be collected regarding the user's performance, analyzed, and used to inform the operator who may in turn edit the process with the goal of improving its execution.

A tool-life prediction method, applicable to a machine tool having a machining end, includes steps of capturing a plurality of measurement data from a tool of the machining end, transforming each of the plurality of measurement data into a corresponding complex process capability index (Cpk), utilizing an artificial neural network being trained to generate a tool-life prediction scale with respect to the Cpk, and then based on the tool-life prediction scale to determine a remaining tool life of the tool. In addition, a tool life prediction system is also provided.

A computer-implemented method for monitoring productivity, health and safety risks posed by activities and objects, and other signals present at industrial sites comprises: receiving data inputs from input devices at an industrial site; selecting a data model that is programmed to detect activities or objects associated with workers or equipment present at the industrial sites; applying the data inputs to the data model to receive output data specifying whether the activities or objects associated with workers or equipment are present at the industrial site; and if they are present: based the output data, determining characteristics of the activities or objects; based on the characteristics, determining whether that the activities or objects cause any productivity, health or safety risks at the industrial site; and if so, generating notifications indicating the health or safety risks at the industrial site.

Apparatuses, methods and storage medium associated with monitoring or assisting in monitoring of an equipment process are disclosed herein. In embodiments, an apparatus may comprise an analyzer to: receive a plurality of simulation results of a plurality of control limit and alert zone combinations for potential use with a control chart to monitor the equipment process, and calculate a plurality of performance metrics for each of the plurality of control limit and alert zone combinations, using the plurality of simulation results. The apparatus may further select an optimal combination of control limits and alert zones, based at least in part on the plurality of performance metrics, and configure an equipment process monitor with the selected optimal combination of control limits and alert zones for use with a control chart to monitor the equipment process. Other embodiments may be described or claimed.

A deterioration degree of a robot body is precisely evaluated. A robot control device 300 includes: a drive control unit 309 controlling operation of a robot body 200; a detection unit 310 detecting a signal used for analysis of a feature amount quantitatively indicating a deterioration degree of the robot body 200 deteriorated over time as the robot body 200 is operated; a determination unit 304 determining whether a data section of the signal includes a constant speed section equal to or greater than a given section; a normalization unit 305 normalizing a signal in a non-constant speed section when the data section of the signal does not include the constant speed section equal to or greater than the given section; an analysis unit 307 analyzing the feature amount; and an estimation unit 308 estimating a remaining life of the robot body 200 based on the feature amount.

A monitoring device for monitoring an operation condition of a machine tool includes: an information acquiring section that acquires event information generated by operation of the machine tool and state information of the machine tool; a judging section that when, after generation of the event information, there has occurred a predetermined change of state of the machine tool corresponding to content indicated by the event information, judges whether or not the content indicated by the event information has been resolved, based on the event information and the state information; and a notifying section that, in the case where when there has occurred the predetermined change of state of the machine tool corresponding to the content indicated by the event information, it has been judged that the content indicated by the event information has not been resolved, re-notifies of the generated event information.

A method for a device to monitor performance of a manufacturing machine which is equipped with a fixture for holding a workpiece, the fixture having at least one fixing hole, includes obtaining actual coordinate values of the fixing hole in a plurality of machining processes and calculating a standard deviation of the coordinates in at least one axial direction according to the actual coordinate values and a preset standard coordinate value. A risk index in at least one axial direction is calculated according to the standard deviation and a preset tolerance and a determination made as to whether risk index exceeds a preset threshold. A warning is sent to the machine and supervising engineer if the risk exceeds the preset threshold. A machine monitoring device and a computer readable storage medium are also provided.

A work support system that is suitable for reducing communication loads and processing loads, and improving certainty and versatility, is provided. An AI manual server 100 generates a rule describing a determination condition of a work situation based on a manual, and transmits the rule to a smart device 300. A work situation determination apparatus 220 comprises a storage section that stores work situation information indicating a work situation in association with equipment signal information. The work situation determination apparatus 220 inputs an equipment signal from a PLC of object equipment 210, reads out the work situation information corresponding to the input equipment signal from the storage section, and transmits the readout work situation information to the smart device 300. The smart device 300 receives the rule, and stores this in the storage section 58. The smart device 300 receives the work situation information from the work situation determination apparatus 220, and displays the work support information on a notification section 52 based on the rule of the storage section 58 and the received work situation information.