Control systems, methods, and algorithms to optimize heat pump and chiller operations
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing control systems for heat pumps and chillers lack a robust framework to optimize operations and minimize energy consumption, relying on outdated software that does not utilize physics and mathematical models, resulting in inefficient energy use and requiring frequent site visits for tuning and high-speed internet access.
Innovation Solution
A hybrid physics and machine learning algorithm that receives sensor data and weather forecasts to generate optimal commands for heat pump/chiller operations, predicting energy-efficient actions and avoiding hardware failures, capable of operating across various configurations and applications without the need for continuous internet access.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of energy
If existing control software is used, then heat pump operations can be monitored for component failures, but energy consumption is not minimized due to lack of physics and mathematical models
Solution Approach 1:
The patent transforms control parameters from simple on/off signals to optimized setpoints derived from physics-based mathematical models. The system continuously calculates optimal operating parameters (temperature, pressure, flow rates) based on thermodynamic equations and system state, enabling energy minimization while maintaining reliable operation.
Solution Approach 2:
The patent replaces traditional empirical control software with a physics-based mathematical model system. Instead of using rule-based or heuristic control algorithms, the system employs fundamental thermodynamic equations to predict system behavior and optimize operations, substituting mechanical trial-and-error tuning with scientific computation.
2Ease of operation
If traditional control systems are used, then installation is simpler, but frequent site visits are required for tuning and maintenance
Solution Approach 1:
The patent implements self-service through automated commissioning capabilities. The system automatically identifies system components, characterizes their performance, and tunes control parameters without requiring technician intervention. The mathematical models adapt to specific system configurations autonomously, eliminating the need for manual tuning during site visits.
Solution Approach 2:
The patent performs preliminary system characterization and model calibration during initial installation. By pre-configuring the mathematical models with system-specific parameters and performance data before operation begins, the system eliminates the need for subsequent tuning visits. All necessary system identification and parameter optimization are completed in advance.
3Power
If cloud-based control systems are used, then data processing capability is enhanced, but high-speed internet access is required continuously
Solution Approach 1:
The patent implements a universal control system that functions autonomously without requiring cloud connectivity. The mathematical models and optimization algorithms are executed locally on the controller, enabling the system to provide full energy optimization, fault detection, and control functions independently. Internet access is optional rather than mandatory, providing flexibility for various installation environments.
4Loss of energy
If physics-based mathematical models are implemented, then energy efficiency is improved, but system complexity increases
Solution Approach 1:
The patent segments the complex thermodynamic system into manageable control zones and subsystems. Each zone has its own simplified mathematical model that captures the dominant physics without requiring full-system complexity. This modular approach allows energy optimization through localized control decisions while keeping individual controller complexity low.
Data Source
AI summary
A method includes receiving condition data including one or more of temperature measurements, pressure measurements, humidity measurements, location coordinates, or a weather forecast for a future time period. The method includes applying, to a predictive machine learning model, the condition data and predictive data generated from a mathematical model of the physical operation of the environment system. The predictive machine learning model is configured to output optimal commands to operational components of the environmental system. The method includes applying the optimal commands to a failure machine learning model. The failure machine learning module is trained to output modified commands that address potential failures in the operational components of the environmental system. The method includes transmitting the modified commands to the operational components of the environmental system.