Method and system for controlling the temperature of a room
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing temperature control systems, such as PID models, are inefficient in maintaining a comfortable room temperature due to high inertia and non-linear thermodynamic characteristics, leading to large temperature fluctuations and energy inefficiency, and neural network-based solutions are resource-intensive and prone to communication errors.
Innovation Solution
A method using a neural network to predict saturation temperatures from a predicted temperature time series, allowing for robust and fault-tolerant temperature control by determining switch-on and switch-off times based on measured indoor temperature changes, reducing the need for continuous model evaluation and minimizing communication channel sensitivity.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If PID control model is used, then the control system is easy to implement, but the temperature fluctuation is large and energy efficiency deteriorates
Solution Approach 1:
The neural network model predicts future saturation temperatures in advance, allowing the control system to switch the temperature control device before the room temperature actually reaches the hysteresis thresholds. This preliminary action prevents temperature fluctuations from exceeding the comfort zone, reducing energy waste while maintaining simple control logic.
Solution Approach 2:
The system continuously monitors room temperature and uses this feedback to update the neural network predictions. By comparing actual temperature measurements with predicted saturation temperatures, the system optimizes switching times to minimize temperature fluctuations and energy consumption while maintaining comfortable conditions.
2Stability of the object's composition
If neural network-based control is used, then temperature fluctuation is reduced, but computational resources and communication reliability requirements increase
Solution Approach 1:
The patent extracts only the essential feature from complex neural network continuous evaluation - the prediction of saturation temperatures at specific switching moments. Instead of continuously evaluating the full neural network model, the system only computes predictions at discrete points when switching decisions are needed, dramatically reducing computational burden while maintaining temperature stability.
Solution Approach 2:
The system uses simplified, discrete neural network predictions rather than continuous complex model evaluation. Each prediction is a computationally inexpensive calculation performed only when needed for switching decisions, replacing the need for resource-intensive continuous model running while achieving similar temperature control effectiveness.
3Measurement precision
If continuous model evaluation is performed, then control precision is improved, but communication channel sensitivity increases
Solution Approach 1:
Instead of continuous model evaluation, the system performs neural network predictions periodically only at discrete switching moments. This periodic action maintains control precision by evaluating temperatures only when switching decisions are required, while dramatically reducing communication frequency and sensitivity to communication channel errors.
Data Source
AI summary
The present invention relates to a method for controlling the temperature of a room (20) provided with a temperature control device (10), in particular for keeping the temperature of the room (20) within a comfort temperature range defined by a lower and an upper hysteresis temperature (TL, TH), characterized in that—measuring the temperature change of a room (20) and generating first and second temperature time series (01, 02) from the measured temperature data, then using a neural network and using the first and second temperature time series (01, 02), we create predicted first and second temperature time series (P1, P2) indicating the future change of time series (01, 02), —determining predicted saturation temperature values (Tsat(P)) for the elements of the predicted first and second temperature time series (P1, P2), as switch-on and switch-off times (tbe, tki), using the neural network and the first and second temperature time series (01, 02), —selecting from the determined predicted saturation temperature values (Tsat(P)) the closest to the corresponding hysteresis temperature (TH, TL), based on which we determine switch-on and switch-off times (tbe, tki). The invention further relates to a system (100) for carrying out such a method.