Siemens Corporation

Siemens Aktiengesellschaft

Siemens Industry, Inc.

Siemens Schweiz Ag

Zhen Song

Sanjeev Srivastava

Arquimedes Martinez Canedo

Yan Lu

Kun Ji

Xianjun Sam Zheng

Lingyun Wang

Yubo Wang

Megan McHugh

Dong Wei

Chellury R Sastry

Xiaofan Wu

Gustavo Arturo Quiros Araya

Florin Darie

Gregory Conte

Guannan Ren

Qinpeng Wang

Rizwan Majeed

Dmitriy Okunev

Yanzi Chen

Mingzhi Cao

Alexander Guiterrez

Donal O'Farrell

Shaili Nepal

Shaopeng Zhang

Mike Veldink

Methods for predictive maintenance with using machine learning in a building automation system and corresponding systems and computer-readable mediums. A method includes receiving device event data corresponding to a device and executing an inference engine to determine root cause fault data corresponding to the device event data. The method includes executing a predictive maintenance engine to produce a survival analysis for the physical device based on the root cause fault data. The method includes producing updated failure data by the predictive maintenance engine, based on the survival analysis, and providing the updated failure data to the inference engine. The inference engine thereafter uses the updated failure data in a subsequent root cause analysis. The method includes outputting the survival analysis.

Systems and methods for HVAC equipment predictive maintenance using machine learning

Methods for data quality analysis and aggregation in a building automation system and corresponding systems and computer-readable mediums. A method includes receiving input data and receiving a configuration file that defines data quality (DQ) processes to be performed on the input data. The method includes dynamically building a configurable pipeline based on the configuration file, the pipeline including one or more Data Quality Indicator (DQI) or Data Quality Aggregation (DQA) process components from a DQ core library. The method includes performing DQ processes on the input data, including executing each of the DQI or DQA process components included in the pipeline, producing one or more DQ results based on the DQ processes, and returning the one or more DQ results.

Systems and methods to assess and repair data using data quality indicators

A system for checking security vulnerabilities for automation system design includes a security database, an Internet crawler application, and security service application. The security database stores descriptions of known software vulnerabilities related to an automation system. The Internet crawler application is configured to systematically browse the Internet to find new software vulnerabilities related to the automation system and index the new software vulnerability into the security database. The security service application retrieves, from the security database, potential software vulnerabilities related to a hardware/software configuration of the automation system. The security service application also identifies policies related to the potential vulnerabilities. Each policy describes a potential vulnerability and action to be performed in response to detection of the potential vulnerabilities. The security service applies the policies to the hardware/software configuration and software code corresponding to an automation application to identify actual vulnerabilities that can be displayed to a user.

System and method to check automation system project security vulnerabilities

Systems and methods are provided for generating a flow control plan for a plurality of components in a flow control system. A decentralized multi-agent control framework is used to plan and schedule for each agent independently without a central processor. Each agent of the multi-agent control framework separately optimizes a local portion of the system as a function of values for one or more parameters. Agents communicate with other connected agents, sharing values for parameters. The communication provides a negotiation and consensus for values of the shared parameters that are used by the agent to recalculate optimized parameters values for the local portion of the system.

Decentralized planning, scheduling and control of multi-agent flow control system

A method of performing failover for programmable logic controllers (PLCs) in an automation environment and controlling a physical system includes an input/output module receiving sensor inputs from field devices and creating a copy of the sensor inputs for a first group of PLC in a first PLC bank. The input/output module transfers the copy the sensor inputs to each PLC in the first group of PLCs and receives processing results from each PLC in the first group of PLCs in response to transferring the copy of the sensor inputs. The input/output module determines whether there are any inconsistencies between the processing results received from each PLC in the first group of PLCs. If there are any inconsistencies between the processing results received from each PLC in the first group of PLCs, a failover control process is initiated by sending a failover control message to a second input/output module.

Resilient failover of industrial programmable logic controllers

An approach that collects sensor data associated with a building automation system having filters and determining the optimal timing of the replacement of filters that includes replacement dates based upon use, utility, and labor costs.

Systems and methods to detect dirt level of filters

A system for using digital twins for scalable, model-based machine predictive maintenance comprises a plurality of digital twins and a simulation platform. The plurality of digital twins correspond to plurality of remotely located physical machines. Each respective digital twin comprises: product nameplate data corresponding to a unique physical machine, one or more simulation models, and a database comprising run time log data collected from sensors associated with the unique physical machine. The simulation platform is configured to process simulation models corresponding to the plurality of digital twins using a plurality of multiprocessor computer systems.

Digital twins for energy efficient asset maintenance

A computer-implemented method of splitting whole building energy consumption includes collecting sensor data from a plurality Variable Air Volume (VAV) boxes in a building, an electric meter in the building, and a gas meter in the building. The total heating energy consumption is split across a plurality of zones within the building using the sensor data, thereby yielding heating energy consumption for each zone. The total cooling energy consumption is split across the plurality of zones using the sensor data, thereby yielding cooling energy consumption for each zone and the total ventilation energy consumption is split across the plurality of zones using the sensor data, thereby yielding ventilation energy consumption for each zone. Zone energy consumption by aggregating the heating energy consumption for the zone, the cooling energy consumption for the zone, and the ventilation energy consumption for the zone.

Building energy split calculation and visualization

A system for calculating total lifecycle costs for a building energy management system includes lifecycle costs for a grid-scale battery system. The system includes a battery lifecycle optimizer configured to provide an optimal battery configuration for a building and a building energy system controller. The building energy system controller receives optimum battery configuration information, information relating to the heat ventilation air conditioning system of the building, intrinsic thermodynamic properties of the building, energy tariff schedules and weather forecast data to forecast a monthly peak demand profile. A simulation is run using a battery model, system model along with tariff and weather information to produce an hourly building energy management plan for minimizing overall energy costs with consideration of system lifecycle costs.

Adaptive demand response method using batteries with commercial buildings for grid stability and sustainable growth

A method for operating an air handling unit of an HVAC system. The method includes opening an outside air flow control device to enable breathing air flow during a high outdoor air time period to a first zone having a first number of occupants and a second zone having a second number of occupants that is less than the first number of occupants. The outside air flow control device is then closed to enable conditioning air flow during a low outdoor air time period to the first and second zones. Further, a variable air volume (VAV) air flow control device provides desired amounts of breathing air to the first and second zones suitable for the first and second number of occupants, respectively. A VAV air temperature control device then provides conditioning air to the first and second zones having a suitable temperature for the first and second number of occupants.

Zonal demand control ventilation for a building

A method of controlling energy consumption in a building includes receiving occupancy data including at least one of occupant request data and occupant schedule data, receiving weather data including at least one of current weather measurement data and weather forecast data, generating an output control signal based on the occupancy data and the weather data, and transmitting the output control signal to a building automation system (BAS) of the building. The occupant request data includes a current request, and the occupant schedule data includes a predicted occupant schedule. The output control signal adjusts a building control device in a zone in the building.

System and method of energy management control

A building has climate control equipment which controls a temperature at different locations. Different locations may be in different control zones controlled by different control devices. An occupant of a location submits a desired location temperature through a user interface on a computing device to a networked server. Setting of a desired temperature is constrained by energy saving policies and by conditions of surrounding locations. An arbitrator device determines based on constraints a new temperature setting. The new temperature setting is accompanied by an energy saving feedback. The occupants confirms the new setting. A climate control device is instructed to apply a device setting to achieve the new temperature. A climate profile of the occupant is learned from previous temperature settings by the occupant.

Social learning softthermostat for commercial buildings

A method of controlling energy consumption in a building. The method includes receiving occupant request data including a plurality of requests, wherein each of the plurality of requests corresponds to one of a plurality of zones in the building wherein the occupant request data is received via a cloud computing resource. The method also includes receiving weather data including at least one of current weather measurement data and weather forecast data wherein the weather data is received via a cloud computing resource. In addition, a facility management rule is received via a cloud computing resource. Further, the method includes generating a plurality of output control signals via cloud computing resource, wherein each of the plurality of output control signals is based on one of a plurality of requests and predicted occupant schedules, energy price data and the facility management rule. The control signals are generated by using simulation-based model predictive control method to determine a set of optimized control signals based on optimized energy use or optimized energy cost. The optimized control signals are transmitted to controllers.

Cloud enabled building automation system

A model predictive control (MPC) framework is enhanced to provide prognostic information and fault tolerant control strategies. A system fault is calculated based on predicted values and is used to generate an internal reference trajectory to which the system is controlled using MPC. If the system fault exceeds a threshold maximum, then the MPC control model is either tuned or reconfigured depending on whether the fault is external or internal.

Growing community of inventors

Plainsboro, NJ, United States of America

Zhen Song