Systems and methods for controlling variable refrigerant flow systems and equipment using artificial intelligence models
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional building systems fail to effectively monitor and manage operating conditions of HVAC equipment, leading to rapid degradation and increased costs due to unmonitored conditions and inefficient oil management in HVAC systems.
Innovation Solution
An oil management controller using machine learning models, such as convolutional neural networks (CNN) and recurrent neural networks (RNN), to predict oil states and conditions, enabling automatic corrective actions like oil replenishment or speed adjustments based on viscosity and quantity.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional building systems are used to monitor HVAC equipment, then system simplicity is maintained, but equipment degradation occurs rapidly due to unmonitored operating conditions
Solution Approach 1:
The system enables self-service by allowing the HVAC equipment to monitor and manage its own oil conditions automatically. The oil management controller continuously analyzes operating data and triggers corrective actions without external intervention, making the system self-diagnosing and self-correcting regarding oil deficiencies
Solution Approach 2:
The patent replaces traditional mechanical monitoring systems with an intelligent electronic system that uses machine learning models. The processing circuit analyzes operating data through software-based algorithms rather than simple mechanical sensors, enabling predictive analytics and automated decision-making for oil management
2Measurement precision
If machine learning models are implemented to predict oil states, then oil management precision is improved, but device complexity increases
Solution Approach 1:
The system performs preliminary action by using machine learning models to predict future oil states before actual deficiencies occur. The processing circuit analyzes current operating data to forecast oil level, viscosity, and other parameters, enabling proactive maintenance before equipment degradation happens
Solution Approach 2:
The patent introduces an intermediary layer between raw sensor data and control decisions. The machine learning model acts as a mediator that processes complex operating data and translates it into actionable insights about oil conditions, bridging the gap between sensor inputs and corrective actions
3Productivity
If automatic corrective actions are initiated for oil deficiencies, then maintenance costs are reduced, but loss of time for system intervention increases
Solution Approach 1:
The system implements continuous feedback by monitoring operating conditions and automatically adjusting oil management based on real-time data. The oil management controller receives feedback from sensors and machine learning predictions, then automatically initiates corrective actions such as oil replenishment or viscosity adjustment without human intervention
Solution Approach 2:
The patent applies dynamics by making the oil management system adaptive and responsive to changing operating conditions. The machine learning models continuously learn from new data, and the control parameters are dynamically adjusted based on current equipment state, enabling the system to optimize maintenance timing and actions
Data Source
AI summary
An oil management controller for heating, ventilation, or air conditioning (HVAC) equipment. The controller includes a processing circuit. The processing circuit is configured to analyze operating data for the HVAC equipment using a machine learning model to predict a variable state or condition of oil used by the HVAC equipment. The processing circuit is configured to identify an oil deficiency based on the variable state or condition of the oil. The processing circuit is configured to automatically initiate a corrective action responsive to identifying the oil deficiency.