Flow control device for an HVAC system
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Building management systems (BMS) face challenges in efficiently optimizing HVAC systems due to high upfront costs and complexity, leading to deferred upgrades until mechanical equipment failure, and existing solutions require manual intelligence and high competency, making them costly and inefficient for legacy buildings.
Innovation Solution
Implementing an agent-based control system with intelligent flow control devices that include valves, sensors, and actuators controlled by software agents, which use learning and optimization algorithms to dynamically adjust system parameters, eliminating the need for additional sensors and reducing mechanical complexity, and can be deployed on legacy systems without manual intervention.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual intelligence and high competency are required for HVAC optimization, then control precision is improved, but device complexity and operational cost increase
Solution Approach 1:
The flow control device performs self-optimization through an embedded learning agent that automatically generates control models and adjusts valve positions based on sensor data, eliminating the need for manual intelligence and high-competency operators while maintaining control precision
Solution Approach 2:
The patent replaces manual control systems with an automated learning agent that uses machine learning algorithms to generate control models, substituting human intelligence with software-based intelligent control that reduces operational complexity
2Measurement precision
If additional sensors are added to improve measurement accuracy, then measurement precision is improved, but device complexity increases
Solution Approach 1:
The patent extracts the function of additional sensors by using existing sensor data more effectively - the learning agent processes data from already-installed sensors to generate accurate control models, eliminating the need for additional sensing hardware while maintaining measurement precision
Solution Approach 2:
The learning agent creates virtual models of system behavior that replicate the information gathering function of additional physical sensors, allowing accurate control decisions without adding physical sensing components
3Loss of energy
If high upfront capital is invested in HVAC upgrades, then energy efficiency is improved, but loss of time increases due to long lead time for return on investment
Solution Approach 1:
The patent changes the control parameters dynamically through machine learning optimization, allowing existing HVAC systems to achieve improved energy efficiency without major hardware upgrades, thereby reducing both upfront capital investment and payback time
Solution Approach 2:
The learning agent continuously adapts control strategies based on real-time sensor data and changing conditions, enabling ongoing energy efficiency improvements that deliver faster returns on investment compared to static upgrade solutions
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A flow control device is configured to control fluid flow in an HVAC system. The flow control device includes a valve, an actuator configured to open and close the valve, and one or more sensors. The flow control device further includes a fault detection and correction agent configured to receive data from the one or more sensors, analyze the data according to a set of rules, and detect whether one or more faults have occurred. In response to detecting a fault, the fault detection and correction agent is configured to either operate the actuator to open or close the valve or initiate a corrective action to he taken by another device in the HVAC system.