Industrial artificial intelligence model aggregation
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 . A system, 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 visualization component configured to generate a visualization of an industrial process comprising devices, wherein the devices are represented in the visualization by a respective models and the models are aggregated to form a supermodel representation of the industrial process; and
a configuration component configured to:
monitor operation of a device, of the devices, that is operating with a first setting, wherein the first setting is represented by a first model in the supermodel representation,
detect an adjustment to the operation of the device, wherein the adjustment indicates that the device is operating with a second setting, and
generate a second model representing operation of the device with the second setting.
2 . The system of claim 1 , further comprising a configuration component configured to:
receive an instruction that includes a requirement for operation of the industrial process;
parse the instruction to identify a target device, of the devices, to which the instruction pertains;
determine an operation of the target device that satisfies the requirement and represent the operation that satisfies the requirement as a third model; and
incorporate the third model into the visualization of the industrial process.
3 . The system of claim 2 , wherein the configuration component is further configured to:
receive a second instruction that includes a second requirement for operation of the target device;
determine a second operation of the first device that satisfies the second requirement and represent the second operation as a fourth model; and
incorporate the fourth model into the visualization of the industrial process.
4 . The system of claim 3 , further comprising an artificial intelligence (AI) component configured to:
review a first prospective model available to represent the second operation of the target device in the industrial process and a second prospective model available to represent the second operation of the target device in the industrial process;
determine which of the first prospective model or the second prospective model best represents the second operation of the target device in view of the requirement; and
in response to determining the first prospective model best represents the second operation, select the first prospective model as the fourth model; or
in response to determining the second prospective model best represents the second operation, select the second prospective model as the fourth model.
5 . The system of claim 1 , wherein the configuration component is further configured to generate a second supermodel representation in which the first model is replaced with the second model.
6 . The system of claim 5 , wherein the visualization component is further configured to replace the supermodel representation of the industrial process with the second supermodel representation.
7 . The system of claim 1 , wherein the industrial process is represented in the visualization by tiers, the tiers comprising at least one of a management level depicting management level components in the industrial process, a production level depicting production level components in the industrial process, a supervisory level depicting supervisory level components in the industrial process, a control level depicting control level components in the industrial process, or a field level comprising field level components in the industrial process.
8 . The system of claim 7 , wherein
the control level comprises a programmable logic controller (PLC) and the field level comprises a sensor, and
the sensor is a smart device configured to generate data in accordance with a requirement of the PLC.
9 . The system of claim 1 , further comprising a configuration component configured to:
review operation of a first device of the devices;
generate a third model that represents operation of the first device;
review operation of a second device of the devices;
generate a fourth model that represents operation of the second device; and
determine a compatibility between the third model and the fourth model.
10 . The system of claim 9 , wherein the configuration component is further configured to:
in response to determining the third model and the fourth model are compatible, incorporate the third model and the fourth model into the supermodel representation.
11 . The system of claim 10 , wherein the configuration component is further configured to determine compatibility between the third model and the fourth model based on a determination that an output of the third model is compatible with an input of the fourth model.
12 . A computer-implemented method for generating a graphical representation of an industrial process, comprising:
generating, by a system comprising a processor, a visualization of an industrial process executed by devices, wherein the generating comprises:
representing the devices in the visualization as respective models, and
aggregating the models to form a supermodel representation of the industrial process;
determining, by the system, that a device, of the devices, is operating in accordance with a first setting;
representing, by the system, operation of the device in accordance with the first setting as a first model in the supermodel representation; and
in response to determining that operation of the device changes from operation in accordance with the first setting to operation in accordance with a second setting:
generating, by the system, a second model representing operation of the device in accordance with the second setting; and
incorporating, by the system the second model into the supermodel representation.
13 . The computer-implemented method of claim 12 , wherein an output of a model, of the models, representing a first device is connected to an input of a model, of the models, representing a second device.
14 . The computer-implemented method of claim 12 , wherein
the generating further comprises generating the visualization based on a requirement defined for the industrial process, and
the computer-implemented method further comprises
determining whether the first model or the second model satisfies the requirement.
15 . The computer implemented method of claim 12 , wherein a first device of the devices is a programmable logic controller and a second device of the devices is a sensor configured to monitor operation of equipment in the industrial process.
16 . A computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to:
generate a visualization of an industrial process performed by devices, wherein the devices are represented in the visualization as respective models, and the models are aggregated to form a supermodel representation of the industrial process;
determine that a device, of the devices, is operating with a first setting;
represent operation of the device with the first setting as a first model;
in response to a determination that operation of the device changes from operation with the first setting to operation with a second setting:
generate a second model representing operation of the device with the second setting; and
incorporate the second model into the supermodel representation.
17 . The computer program product of claim 16 , wherein the program instructions are further executable by the processor to cause the processor to:
generate the supermodel representation in accordance with a defined requirement for the industrial process; and
determine whether the first model or the second model satisfies the defined requirement.
18 . The computer program product of claim 16 , wherein an output of a model, of the models, representing a first device, connects to an input of a model, of the models, representing a second.
19 . The computer program product of claim 16 , wherein the program instructions are further executable by the processor to cause the processor to:
determine whether an output of a model, of the models, representing a first device is compatible with an input of a model, of the models, representing a second device; and
in response to determining that the output is compatible with the input, incorporating the model representing the first device and the model representing the second device into the supermodel representation of the industrial process, with the output connected to the input.
20 . The computer implemented method of claim 12 , wherein the generating of the visualization comprises representing the industrial process in the visualization by tiers, the tiers comprising at least one of a management level depicting management level components in the industrial process, a production level depicting production level components in the industrial process, a supervisory level depicting supervisory level components in the industrial process, a control level depicting control level components in the industrial process, or a field level comprising field level components in the industrial process.