Automated control-schedule acquisition within an intelligent controller
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current control systems lack the flexibility and intelligence to adapt and produce desired operational behaviors specified after controller design and implementation, particularly in dynamic environments where traditional design techniques are insufficient.
Innovation Solution
Intelligent controllers that learn and modify control schedules over time through aggressive and steady-state learning phases, utilizing sensor feedback and user inputs to encode desired operational behaviors into control schedules, enabling adaptive control of devices, machines, and systems.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If traditional control design techniques are used, then the controller can ensure predetermined system behavior under normal operational conditions, but the controller lacks flexibility and intelligence to adapt to desired operational behaviors specified after controller design and implementation
Solution Approach 1:
The controller performs self-learning by automatically acquiring control schedules through monitoring sensor feedback and user inputs during aggressive and steady-state learning phases, without requiring external reprogramming or complex configuration interfaces
Solution Approach 2:
The controller continuously monitors sensor feedback from the controlled system and uses this feedback to refine and update control schedules over time, enabling adaptive behavior while maintaining relatively simple controller architecture
2Productivity
If the controller aggressively learns during initial phase, then the controller quickly acquires control schedules, but the learning process requires frequent immediate-control inputs and consumes more resources
Solution Approach 1:
The controller dynamically adjusts its learning behavior between two distinct phases: an initial aggressive learning phase that prioritizes quick acquisition of control schedules, and a subsequent steady-state phase that minimizes energy consumption by reducing the frequency of immediate-control inputs while continuing to refine schedules
Solution Approach 2:
The controller implements periodic learning cycles with different characteristics - intensive learning periods followed by consolidation periods where learned schedules are applied with minimal intervention, creating a rhythm of high and low resource consumption that balances learning speed with energy efficiency
Data Source
Figure 1
Figure 2
Figure 3
AI summary
The current application is directed to intelligent controllers that initially aggressively learn, and then continue, in a steady-state mode, to monitor, learn, and modify one or more control schedules that specify a desired operational behavior of a device, machine, system, or organization controlled by the intelligent controller. An intelligent controller generally acquires one or more initial control schedules through schedule-creation and schedule-modification interfaces or by accessing a default control schedule stored locally or remotely in a memory or mass-storage device. The intelligent controller then proceeds to learn, over time, a desired operational behavior for the device, machine, system, or organization controlled by the intelligent controller based on immediate-control inputs, schedule-modification inputs, and previous and current control schedules, encoding the desired operational behavior in one or more control schedules and/or sub-schedules.