Intelligent Controller Feedback Modeling for Time-to-Target Display
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Intelligent controllers lack the ability to continuously and accurately calculate and display the time remaining until a control task is completed, particularly in complex environments where multiple factors influence the control parameters, leading to inaccurate predictions and user dissatisfaction.
Innovation Solution
The implementation of intelligent controllers that use multiple models for time behavior, collecting data to predict the time remaining until specified parameters are reached, and displaying this information to users, with specific examples demonstrated in the context of an intelligent thermostat, employing both global and local modeling techniques to refine predictions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional control systems are used, then device complexity is low, but the ability to accurately predict and display time remaining until target state is poor
Solution Approach 1:
The system performs preliminary actions by continuously collecting operational data and pre-building multiple predictive models during normal operation. These models are prepared in advance to quickly provide accurate time-to-target predictions when needed, without requiring complex real-time calculations during critical moments.
Solution Approach 2:
The patent introduces intermediary predictive models as mediators between the raw sensor data and the user interface. These models process and interpret complex environmental data to generate simple, actionable time predictions displayed to users, bridging the gap between complex system state and user-friendly information.
2Measurement precision
If multiple models are used for prediction, then prediction accuracy improves, but computational requirements and processing time increase
Solution Approach 1:
The predictive system is segmented into multiple specialized models, each handling specific aspects of time behavior prediction. This segmentation allows the system to distribute computational load across different models rather than requiring one complex monolithic model, improving accuracy while managing energy consumption through divided responsibility.
Solution Approach 2:
The system dynamically changes parameters by selecting and weighting different predictive models based on current environmental conditions and data availability. This allows the system to adapt computational resources to actual needs, using more complex models only when necessary and simpler models when sufficient, thereby optimizing energy consumption.
3Reliability
If continuous data collection and model updating is performed, then prediction reliability improves, but processing load and system complexity increase
Solution Approach 1:
The system implements continuous feedback loops where prediction results are monitored and used to refine future predictions. Actual system behavior is compared against predicted behavior, and model parameters are adjusted based on this feedback, continuously improving reliability without requiring complete system redesign.
Solution Approach 2:
The predictive models perform self-service by automatically updating themselves using collected operational data. The system autonomously refines its own predictive accuracy through continuous learning from actual system behavior, reducing the need for manual intervention and complex external processing infrastructure.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
The current application is directed to intelligent controllers that continuously, periodically, or intermittently calculate and display the time remaining until a control task is projected to be completed by the intelligent controller. In general, the intelligent controller employs multiple different models for the time behavior of one or more parameters or characteristics within a region or volume affected by one or more devices, systems, or other entities controlled by the intelligent controller. The intelligent controller collects data, over time, from which the models are constructed and uses the models to predict the time remaining until one or more characteristics or parameters of the region or volume reaches one or more specified values as a result of intelligent controller control of one or more devices, systems, or other entities.