Environment controller and method for inferring via a neural network one or more commands for controlling an appliance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current environment control systems fail to generate optimal commands for appliances based on a combination of current environmental conditions and set points, as they do not adequately consider multiple and complex criteria such as comfort, stress on components, and energy consumption, leading to either overly simplistic or overly complex rule sets.
Innovation Solution
An environment controller equipped with a neural network inference engine that uses a predictive model generated by a training engine to infer commands for controlling appliances, considering environmental characteristic values and set points, thereby optimizing command generation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a set of rules is implemented to generate commands considering current environmental characteristic values and set points, then the adequacy of commands can be improved, but the complexity of the rule set becomes too complicated to be designed by a human being
Solution Approach 1:
The patent replaces the mechanical system of human-designed rule sets with an artificial intelligence-based neural network system. The neural network is trained to automatically generate optimal commands by learning from historical data, thereby substituting the complex, hard-to-design rule-based approach with a data-driven model that can handle multiple inter-related criteria without requiring explicit programming of complex rules.
2Ease of manufacture
If a simple set of rules is implemented to generate commands, then the ease of design is improved, but the effectiveness of command generation becomes insufficient
Solution Approach 1:
The patent replaces simple but ineffective rule-based systems with a neural network-based intelligent system. The neural network is trained on comprehensive datasets that capture complex relationships between environmental conditions, set points, and optimal commands, enabling the system to generate effective commands without requiring complex manual rule design.
Solution Approach 2:
The patent employs a preliminary training phase where the neural network is trained offline using historical operational data. This preliminary action allows the system to learn optimal command generation strategies in advance, so that during actual operation, the system can quickly and effectively generate commands without needing to process complex rules in real-time.
3Ease of operation
If commands are generated to achieve quick convergence from current temperature to target temperature, then the comfort of people is improved, but the stress imposed on components and energy consumption increase significantly
Solution Approach 1:
The patent uses a dynamic command generation approach where the neural network adjusts commands based on real-time environmental conditions and system state. Rather than applying fixed aggressive control rules, the neural network dynamically determines optimal command magnitudes that balance comfort requirements with energy efficiency, adapting its behavior to current conditions.
Solution Approach 2:
The system incorporates feedback mechanisms where the neural network continuously monitors environmental characteristic values and adjusts commands accordingly. This feedback loop allows the system to learn from past actions and their outcomes, optimizing the balance between achieving target conditions quickly and minimizing energy consumption and component stress over time.
Data Source
AI summary
Method and environment controller for inferring via a neural network one or more commands for controlling an appliance. A predictive model generated by a neural network training engine is stored by the environment controller. The environment controller receives at least one environmental characteristic value (for example, at least one of a current temperature, current humidity level, current carbon dioxide level, and current room occupancy). The environment controller receives at least one set point (for example, at least one of a target temperature, target humidity level, and target carbon dioxide level). The environment controller executes a neural network inference engine, which uses the predictive model for inferring the one or more commands for controlling the appliance based on the at least one environmental characteristic value and the at least one set point. The environment controller transmits the one or more commands to the controlled appliance.