System level industrial artificial intelligence aggregation of baseline data deviation
Various systems and methods are presented regarding monitoring and controlling operation of a process. A visual representation of the process can be created based on a supermodel comprising models (representing one or more devices) and nodes (representing respective device variables and constraints). Further, the process can be represented by levels, wherein devices at each level can be self-aware and have onboard artificial intelligence, such that a device at any level can auto-configure itself in accordance with a requirement placed upon it. Field-level devices (IFLDs) can be smart devices which auto-configure based upon a requirement from a higher-level device. Accordingly, system awareness can be incorporated across all levels of the process enabling overall and device-specific optimization of the process. IFLDs can auto-configure to collect and transmit data in accordance with an instruction from a higher-level device, leading to efficient data collection, reduced data bandwidth/processing, and expedited system optimization.
1 . An industrial device, comprising:
a memory that stores computer executable components; and
a processor that executes the computer executable components stored in the memory, wherein the computer executable components comprise:
a configuration component configured to implement a first configuration on the industrial device, wherein the first configuration controls a first operation of the industrial device; and
an artificial intelligence (AI) component configured to, in response to receipt of an instruction, parse the instruction to extract a requirement included in the instruction pertaining to operation of the industrial device, and determine a second configuration that satisfies the requirement,
wherein the configuration component is further configured to implement an auto-configure operation of the industrial device, wherein the auto-configuration implements the second configuration on the industrial device, and the second configuration controls a second operation of the industrial device in accordance with the instruction.
2 . The industrial device of claim 1 , wherein the industrial device is an intelligent field-level device (IFLD) operating in a process.
3 . The industrial system of claim 2 , wherein the IFLD is one of a sensor, an actuator, a valve, an industrial controller, a motor drive, a telemetry device, a meter, a device that monitors operation of a component or unit of equipment included in the process, or a device controls operation of the component or unit of equipment.
4 . The industrial device of claim 1 , wherein
the industrial device is a first intelligent field-level device (IFLD), and
the instruction is received from a second IFLD communicatively coupled to the first IFLD or from a programmable logic controller (PLC) communicatively coupled to the first IFLD.
5 . The industrial device of claim 1 , wherein the instruction relates to at least one of:
formatting output signals received from a component that the industrial device is configured to monitor,
parsing output signals received from a component, wherein the parsing results in a subset of the output signals being transmitted by the industrial device to another device, or
monitoring output signals received from a component to determine deviation from a baseline value.
6 . The industrial device of claim 1 , wherein the AI component is further configured to monitor operation of the industrial device with the second configuration to determine whether operation of the industrial device is performing in accordance with the requirement.
7 . The industrial device of claim 1 , wherein the AI component utilizes at least one of parametric modeling, parametric hybrid modeling, linear modeling, single value modeling, non-linear modeling, kinetic parameters, empirical modeling, first principles reasoning, incremental prioritization, solvers, historical data mining, cost function analysis, regression cost function, binary classification cost functions, multi-class classification cost functions, mixed integer non-linear programming, deep learning techniques, backpropagation, static backpropagation, recurrent backpropagation, gradient computation, chain rule, or error determination to determine the second configuration.
8 . The industrial device of claim 1 , further comprising a historian component configured to analyze historical data to determine the second configuration, wherein the historical data comprises at least one of a prior configuration utilized at the industrial device, prior data generated by the industrial device, specification data of the industrial device, or object-orientated data.
9 . The industrial device of claim 1 , wherein
the configuration component is further configured to generate a computer representation of operation of the industrial device, and
the computer representation is at least one of a model or a node configured to be incorporated into a visual representation of a process that includes the industrial device.
10 . A computer-implemented method for controlling operation of a device in an industrial process, comprising:
implementing, by the device, a first configuration, wherein the first configuration controls a first operation of the device;
receiving, by the device, an instruction that relates to data processing performed by the device;
in response to the receiving, parsing, by the device, the instruction to extract a requirement included in the instruction pertaining to the data processing;
determining, by the device, a second configuration that satisfies the requirement; and
implementing, by the device, a second configuration on the device, wherein the second configuration controls a second operation of the device in accordance with the instruction.
11 . The computer-implemented method of claim 10 , wherein the device is an intelligent field-level device (IFLD) operating in the industrial process, the IFLD comprising one of a sensor, an actuator, a valve, an industrial controller, a motor drive, a telemetry device, a meter, a device that monitors operation of a component or unit of equipment included in the process, or a device that controls operation of the component or unit of equipment.
12 . The computer-implemented method of claim 11 , wherein
the instruction further comprises a third configuration,
the third configuration is a configuration pertaining to control of equipment included in the industrial process and communicatively coupled to the device; and
the method further comprises implementing, by the device, the third configuration on the equipment to facilitate control of the equipment by the device.
13 . The computer-implemented method of claim 10 , wherein
the device is a first device operating in the industrial process, and
the instruction is received from a second device communicatively coupled to the first device.
14 . The computer-implemented method of claim 13 , wherein the first device is an intelligent field-level device and the second device is a programmable logic controller.
15 . The computer-implemented method of claim 14 , wherein
the first device processes output data received from equipment included in the industrial process, and
the equipment is communicatively coupled to the first device, and the data is processed in accordance with the instruction received from the second device.
16 . A computer program product comprising a non-tangible computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to:
implement a first configuration on a device, wherein the first configuration controls a first operation of the device in an industrial process;
receive an instruction, wherein the instruction relates to data processing performed by the device;
parse the instruction to extract a requirement included in the instruction pertaining to operation of the device;
determine a second configuration based on at least one of implementation of an artificial intelligence (AI) operation to identify an operation of the device that satisfies the requirement, or analysis of historical data to identify a prior configuration that satisfies the requirement; and
perform an auto-configuration operation at the device to implement the second configuration on the device, wherein the second configuration controls a second operation of the device in accordance with the instruction.
17 . The computer program product of claim 16 , wherein the device is one of a sensor, an actuator, a valve, an industrial controller, a motor drive, a telemetry device, a meter, a device that monitors operation of a component or unit of equipment included in the process, or a device that controls operation of the component or unit of equipment.
18 . The computer program product of claim 16 , wherein the instruction relates to at least one of:
formatting output signals received from a component that the device monitors,
parsing output signals received from a component, wherein the parsing results in a subset of the output signals being transmitted by the device to a second device, or
monitoring output signals received from a component to determine deviation from a baseline value.
19 . The computer program product of claim 16 , wherein the program instructions are further executable by the processor to cause the processor to monitor operation of the device with the second configuration to determine whether operation of the device is performing in accordance with the requirement.
20 . The computer program product of claim 16 , wherein the historical data comprises at least one of a prior configuration utilized on the device, prior data generated by the device, specification data for the device, or object-orientated data.