Heuristic method of automated and learning control, and building automation systems thereof
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current building automation systems lack a unified operational model to effectively manage energy interrelationships and adapt to complex, ad hoc building topologies, relying on model-free control loops that are difficult to optimize and require human intervention, limiting their ability to scale and perform continuous commissioning.
Innovation Solution
A closed-loop, heuristically tuned, model-based control algorithm that simulates external factors like weather and occupancy, allowing for adaptive control and real-time monitoring, enabling the system to automatically adjust and optimize operations by creating and evolving mathematical models of building systems.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If model-free control loops are used, then simplicity of implementation is achieved, but ability to manage sophisticated tightly-coupled systems and adaptively tune complex models deteriorates
Solution Approach 1:
The patent introduces a unified operational model as an intermediary layer between the control system and building components. This model serves as a mediator that captures complex interrelationships between HVAC, lighting, and other building systems, enabling the simple controller to manage sophisticated tightly-coupled systems through the intermediary's structured representation of system dynamics and interactions.
2Measurement precision
If automated commissioning requires occupancy-free training period, then system can be trained with artificial test regime, but potential for retro-commissioning or continuous commissioning is limited
Solution Approach 1:
The patent implements dynamic commissioning capabilities that allow the system to be trained and retrained at any time without requiring occupancy-free periods. The unified operational model enables continuous learning from live building data, allowing retro-commissioning of existing buildings and ongoing optimization as building conditions change, making the commissioning process adaptive rather than static.
3Ease of operation
If existing approaches are limited to simple HVAC systems with known topologies, then commissioning process is simplified, but ability to scale to complex ad hoc arrangements deteriorates
Solution Approach 1:
The patent creates a universal unified operational model that can represent diverse building topologies and system configurations through a common framework. This universal model handles everything from simple HVAC systems to complex ad hoc arrangements of interconnected subsystems, allowing the same commissioning approach to scale across different building types and complexities without requiring topology-specific methods.
4Measurement precision
If physical model based approaches require highly skilled engineering team, then model accuracy can be maintained, but applicability to projects without such resources deteriorates
Solution Approach 1:
The patent implements self-service capabilities where the unified operational model automatically learns and adapts to the specific building through live data collection and analysis. The system performs its own commissioning and optimization without requiring highly skilled engineering teams, as the model-driven approach with automated heuristic tuning enables non-experts to achieve accurate, customized building models that adapt to actual operating conditions.
5Ease of manufacture
If building controls are model-free, then implementation is simple, but ability to provide self-knowledge and model-driven graphical programming deteriorates
Solution Approach 1:
The patent applies preliminary action by establishing a unified operational model before control operations begin. This pre-established model contains the building's system interrelationships, constraints, and operational characteristics, providing the controller with advance knowledge needed for model-driven graphical programming and intelligent decision-making, rather than learning these relationships in real-time during operation.
Data Source
AI summary
Apparatuses, systems, and methods of physical-model based building automation using in-situ regression to optimize control systems are presented. A simulation engine is configured to simulate a behavior or a controlled system using a physical model for the controlled system. A data stream comprises data from a controlled system. A training loop is configured to compare an output of a simulation engine to a data stream using a heuristic so that a physical model is regressed in a manner that the output of the simulation engine approaches the data stream.