The systems and methods provide an action recognition and analytics tool for use in manufacturing, health care services, shipping, retailing and other similar contexts. Machine learning action recognition can be utilized to determine cycles, processes, actions, sequences, objects and or the like in one or more sensor streams. The sensor streams can include, but are not limited to, one or more video sensor frames, thermal sensor frames, infrared sensor frames, and or three-dimensional depth frames. The analytics tool can provide for kitting products, including real time verification of packing or unpacking by action and image recognition.

A collector included in a data collection apparatus performs data collection to collect data from a PLC. A controller included in the data collection apparatus determines whether the collector is valid depending on whether the collector at a time when an instruction to start the data collection is provided matches the collector at a preset time, and causes the collector to start the data collection in response to the collector being valid.

A data analysis apparatus generates M (M is an integer of 3 or greater) groups each including data regarding a plurality of units from data where first KPIs and K (K is an integer of 2 or greater) explanatory variables are given by 1:1, generates a second KPI indicating the state of the group based on the values of a plurality of first KPIs included in the group, and selects a feature for the first KPIs based on a correlation analysis between the second KPI of each group and the feature of each group calculated based on the explanatory variables.

A method for automatically determining a current condition of a system in operation includes acquiring first data relating to one or more faults in the system during a process, acquiring second data relating to a process time in the system during the process, acquiring third data relating to media and energy consumption in the system during the process, and determining a process indicator number based on the first, second, and third data. A device for automatically determining a current condition of a system in operation is configured to carry out the method.

Systems and methods for asset management are provided. Event data characterizing events experienced by assets distributed among different sites of a fleet is maintained. The event data includes an asset location within an asset hierarchy of the fleet and an event parameter corresponding to the event. A graphical user interface (GUI) is generated that displays a first window including a hierarchical list of assets organized according to their position within the asset hierarchy. When the GUI receives a selection of a level within the hierarchical list, events associated with the selected level can be identified. Identified events can be classified based upon their event data as a unique event having a single occurrence or a repeat event having multiple occurrences. In response to receipt of the selection, the GUI is updated to display a second window listing single entries for respective unique events and single entries for respective repeat events.

In accordance with exemplary embodiments, methods and systems are provided for designing a manufacturing system. In an exemplary embodiment, a method for designing a manufacturing system includes: identifying a potential hazard for the manufacturing system; evaluating, via a processor, the potential hazard with respect to a plurality of possible injuries associated with the potential hazard; and providing output, via instructions provided by the processor, with respect to the potential hazard based on the evaluating of the potential hazard with respect to the plurality of possible injuries associated with the potential hazard.

Systems and methods for high spatial and temporal resolution of environmental observations. Improved resolution is achieved by using machine learning methods to build a function from observations from frequently measuring stationary sensors to another sensor in a different location at a corresponding time. Given values from the reference sensor, the learned function can impute sensor measurements in unobserved locations and times.

A system and method including receiving historical time series sensor data associated with operation of an industrial asset; generating visual representation images of scatter plots based on the historical time series sensor data based on a reference to a digitized knowledge domain associated with the industrial asset; assigning a root cause label to each image; generating a convolutional neural network (CNN) model trained and tested using subsets of the labeled images; and processing, by the CNN model, a real-time image to detect at least one anomaly in the real-time image and one or more root causes associated with the at least one anomaly.

A method for operating a condition monitoring system of a vibrating machine in the form of a vibrating conveyor or a vibrating screen, it is provided that the condition monitoring system has at least one sensor designed for motion detection and/or acceleration detection, which is mounted on the vibrating machine. The sensor generates measurement data, which is further processed into characteristic values in a processing unit associated with the sensor. The characteristic values are stored as a data set or a plurality of data sets. The data sets and/or the data sets expanded to include metadata are transferred to a data storage and stored there. A knowledge base for an expert system is generated taking into account the information provided by the data sets and/or built on theoretical models.

The invention relates to: a method for monitoring a process engineering installation, in which a model of the process engineering installation is used to ascertain values of at least one performance parameter of the process engineering installation from actual values of at least one operating parameter of the process engineering installation that occur during operation of the process engineering installation, wherein the model is used to ascertain comparison values of the at least one performance parameter of the process engineering installation from setpoint values of the at least one operating parameter, and wherein mutually corresponding values and comparison values of the at least one performance parameter are taken as a basis for ascertaining at least one performance gap in the operation of the process engineering installation and to a process engineering installation.