Siemens Aktiengesellschaft

Siemens Corporation

Georgia Tech Research Corporation

Siemens Industry, Inc.

Siemens Aktiengesell Schaft

Lingyun Wang

Arquimedes Martinez Canedo

Hartmut Ludwig

Justinian Rosca

Steffen Lamparter

George Lo

Juan L Aparicio Ojea

Zhen Song

Thomas Gruenewald

Florian Ersch

Holger Strobel

Sven Hermann

Ziyan Wu

Sanjeev Srivastava

Leandro Pfleger De Aguiar

Michael J Wynblatt

Dong Wei

Yan Lu

Sindhu Suresh

Mareike Kritzler

Hasan Sinan Bank

Stephan Grimm

Farshid Arman

Raffaello Lepratti

Kurt Dirk Bettenhausen

Tao Cui

Thomas R Kurfess

Emmanuel Bisse

Fernando Garcia-Perez

Naveen Kumar Singa

Phani Ram Kumar Kuruganty

Dmitriy Okunev

Thomas Kurfess

Michael Jaentsch

Florian Erseh

Hermann Friedrich

Stephanie Locks

Aoyu Chen

Dongmin Han

Nuodi Huang

Alessandra Oliveira Da Silva

Roby Lynn

Bogdan Rosca

Bernardo Hermont

Michael Wynblatt

Harmut Ludwig

A system for processing data in an industrial environment includes a sensor that communicates sensor data acquired from a factory floor as a multicast data stream where each frame is tagged with a sequence identifier indicative of a position of that frame in the data stream. A network switch distributes the data stream to a group of multicast endpoints. The system includes a controller with a plurality of modularly connected processing units. Each processing unit is further connected to the network switch and configured as a respective endpoint of the group of multicast endpoints. Each processing unit selectively processes frames of the data stream in dependence of the sequence identifier of individual frames by executing a data processing module, to produce an output result associated with each processed frame. The controller assembles the output result and the sequence identifier of each processed frame from the plurality of processing units.

System and method for enabling scalable processing throughput of high-volume data on industrial controllers

A system and method for constructing a reconfigurable runtime system used in an automation system using reusable runtime functions (RRFs) is disclosed. A specialization module executes a specialization operation to configure or customize at least one RRF to satisfy functional requirements of the automation system. A stitching module executes a stitching operation that connects output of at least one RRF to input of one or more other RRFs. A stacking module executes a stacking operation that stacks RRFs as layers to create new abstractions, functionality and services. The specialization operation, the stitching operation, and the stacking operation are performed according to a runtime specification language.

System and method for adapting a reconfigurable runtime system used in automation systems

A system for providing access to locally stored process image data to other devices in an industrial production environment includes a plurality of controller devices and a process image backbone. Each respective controller device comprises the following: a volatile computer-readable storage medium comprising a process image area; a non-volatile computer-readable storage medium; a control program configured to provide operating instructions to a production unit; an input/output component configured to update the process image area during each scan cycle or upon the occurrence of one or more events with process image data items associated with the production unit; and a historian component configured to locally store the process image data items of the process image area as time series data in the non-volatile computer-readable storage medium. The process image backbone provides the plurality of controllers with uniform access to the process image data items of each programmable logic device.

Universal data access across devices

HMI screens are typically manually engineered or arranged. For example, HMI screens can include various elements, and an engineer often arranges the HMI elements on a given HMI screen, for instance one by one, until the final design of the HMI screen is complete. It is recognized herein that existing approaches to designing and arranging HMI screens lack efficiency, and can be tedious and redundant. Method, systems, and apparatuses described herein can automatically arrange elements of human-machine interface (HMI) screens. In an example aspect, a computing system includes a deep learning model, for instance an autoencoder or a generative adversarial network (GAN), configured to learn and design HMI screen arrangements.

Automatic arrangement of HMI screens

Service interfaces and data topics can be discovered and retrieved so as to bridge different industrial automation ecosystems, programming languages, platforms, and the like, together. For example, nodes of one ecosystem can discover endpoints (e.g., interfaces and topics) across heterogeneous incompatible ecosystems, without changing the ecosystem. Further, endpoint descriptions are managed across heterogeneous incompatible ecosystems. Endpoint descriptions can be automatically generated based on interface and topic description in an interface description file. Such descriptions can also be automatically exported into registries of other ecosystems.

Endpoint registry across ecosystems

A system for exchanging data in an automation environment is provided. The system includes at least one programmable logic controller (PLC A) containing program instructions executable by the at least one programmable logic controller and a queue block () configured to dynamically exchange data between the program instructions of the PLC and a data consumer (PLC C, PLC D).

Queue blocks for flexible automation engineering programs

A system and a method provide an Artificial Intelligence (AI) companion for each Function Block in a Programmable Logic Controller (PLC) program to integrate AI in automation systems. Multiple function blocks and system function blocks are grouped into a logic group. A control problem is broken down from a top level into logical partitions as several functions that are programmed as Function Blocks in a PLC program. Each Function Block and the entire PLC program are integrated with an associated AI Companion. A runtime system for the AI Companion provides new runtime capabilities. An approach to implementing the AT Companions is provided. A method of controlling an automation process is also provided.

Artificial intelligence (AI) companions for function blocks in a programmable logic controller (PLC) program for integrating AI in automation

A hyperlink message for machine-to-machine (M2M) or machine-to-human (M2H) communication has a semantic metadata tag, a content field, an executable specification field. Executable specification instructs a machine to perform a task associated with the machine related data, and post to a machine social media platform results of the task as content for the hyperlink message. The hyperlink message posting is visible and available to other participating machines on the machine social media platform to read and contribute related content as a hyperlink discussion of M2M or M2H communication.

Hyperlink messages for machine-to-machine communication on a machine social media platform

An automation system and a method of injecting transactional services in automation is provided. The method performed by the automation system comprises providing a gatekeeper for deployment access control to determine which components can be deployed by an abstraction layer. The method further comprises providing a plugin interface between a consumer plugin associated with a first automation function and a provider plugin associated with a second automation function. The method further comprises injecting an interceptor plugin associated with a transactional service of the transactional services between the consumer plugin and the provider plugin based on an interceptor design pattern.

Automation system and a method for injecting transactional services in automation

A system for managing physical assets in a manufacturing system includes a plurality of product controllers corresponding to physical assets in the manufacturing system. Each product controller is configured to store a desired product state for a physical asset and collect sensor data received from other digital companions. Furthermore, each product controller determines an actual product state based on the collected sensor data, as well as one or more actions to be performed on one or more physical assets in the manufacture system to yield the desired product state. Once the actions are determined, the product controller transmits control instructions for performing the one or more actions to one or more operation controllers in the manufacturing system.

Product closing the loop

A method of operating an intelligent programmable logic controller (PLC) as part of a production process within an automation system includes the intelligent PLC receiving automation system data and a semantic context model comprising a plurality of ontologies providing formal specifications of conceptual entities associated with the automation system. The intelligent PLC creates one or more semantic annotations for the automation system data using the semantic context model. These semantic annotations are stored along with the automation system data in a non-volatile storage medium included in the intelligent PLC.

Rich contextualization of automation data

A method for performing security failover in an industrial production environment includes a programmable logic controller (PLC) receiving notification that a function block (FB) or a function (FC) on the programmable logic controller has been maliciously revised. The PLC next determines whether the function block or the function is also maliciously revised on a failover computing device. If the failover computing device is not maliciously revised, a failover operation is performed by the PLC. This operation includes sending a data block comprising one or more input parameters to the function block or the function and receiving an output data resulting from executing the function block or the function with the data block on the failover computing device.

Cyberattack-resilient control system design

A computer-implemented method of identifying federations of manufacturing apps using House of Quality (HoQ) analysis includes receiving user request information comprising a plurality of desired functions and an importance value for each of the plurality of desired functions and generating a correlation matrix between the plurality of apps, wherein each element of the correlation matrix indicates a degree of correlation between a pair of apps. A relationship matrix is generated which comprises numerical values indicating relationships between a plurality of apps and the plurality of desired functions, wherein each column of relationship matrix is associated with an app and each row is associated with a desired function. Next, a weighted matrix is created by multiplying each row in the relationship matrix by the importance value corresponding to the desired function associated with the row. The numerical values in each column of the weighted matrix are aggregated to determine a total value for each of the plurality of apps. A federation of apps is identified based on the correlation matrix and the total values determined for the plurality of apps.

House of quality for federated manufacturing apps

A model-based human machine interface (HMI) system is provided. The HMI system includes a plurality of output devices each having output capabilities that include at least one unique output capability level and a semantics library that is configured to receive SUC component models each having an output format and data. The semantics library is configured to analyze the data relative to the SUC component models and to transmit each of the SUC component models to one or more of the plurality of output devices. The one or more of the plurality of output devices are selected based on a correlation between the output capabilities of the plurality of output devices and the output format of the SUC component models.

Model-based human machine interface (HMI)

A method of operating an intelligent programmable logic controller includes executing, by a processor included in the intelligent programmable logic controller, a control program. A non-volatile storage medium included in the intelligent programmable logic controller stores a control model comprising control knowledge related to the control program. The control model is used to perform a monitoring operation related to execution of the control program on the intelligent programmable logic controller.

Control contextualization and reasoning about control

Growing community of inventors

Princeton, NJ, United States of America

Lingyun Wang