Self-Learning Pump and Fan Control Without External Sensors
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing control systems for temperature and flow control, such as those used in pumps and fans, often fail to optimize energy use and efficiency due to reliance on external sensors and fixed operation points, leading to suboptimal performance as environmental conditions change.
Innovation Solution
A self-learning control system that detects internal device properties like power and speed to infer output variables like pressure and flow, allowing for dynamic adjustment of operation points to achieve setpoints efficiently without external sensors, using a control curve to optimize energy use and adapt to changing conditions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Use of energy by moving object
If external sensors and fixed operation points are used for control, then system structure is simple, but energy optimization capability deteriorates
Solution Approach 1:
The control system uses the device's own operational data (power consumption, speed) to infer output variables and optimize its operation. The system serves itself by using internal measurements rather than external sensors, enabling energy optimization through self-monitoring and self-adjustment based on detected input variables and model predictions
Solution Approach 2:
The patent replaces external sensor-based measurement systems with a computational approach that infers output variables from input variables using mathematical models. Instead of mechanically measuring pressure and flow with external sensors, the system substitutes this with computational inference based on power consumption and speed data combined with system models
2Measurement precision
If external sensors are used to detect output variables, then measurement accuracy is high, but device complexity increases
Solution Approach 1:
The patent introduces mathematical models as intermediaries between input variable measurements and output variable determination. Instead of directly measuring output variables with external sensors, the system uses models that compute output variables from input variables, serving as a computational mediator that eliminates the need for additional physical sensors
Solution Approach 2:
The system creates computational copies of the physical measurement process by using mathematical models to represent the relationship between input and output variables. These model-based copies allow the system to determine output variables without physical duplication through external sensors
3Adaptability or versatility
If fixed operation points are used for control, then system stability is maintained, but adaptability to changing conditions deteriorates
Solution Approach 1:
The control system transitions from fixed operation points to dynamic operation points that continuously adapt to changing conditions. The system detects current input variables, uses models to predict optimal operation points, and adjusts accordingly, making the control parameters dynamic rather than static while maintaining stability through controlled adaptation
Solution Approach 2:
The system implements feedback by continuously detecting input variables, comparing actual operation with model predictions, and adjusting operation points based on this feedback loop. This allows the system to adapt to changing conditions while maintaining stability through continuous monitoring and adjustment rather than fixed setpoints
Data Source
AI summary
A control system for an operable system such as a flow control system or temperature control system. The system operates in a control loop to regularly update a model with respect at least one optimizable input variable based on the detected variables. The model provides prediction of use of the input variables in all possible operation points or paths of the system variables which achieve an output setpoint. In some example embodiments, the control loop is performed during initial setup and subsequent operation of the one or more operable elements in the operable system. The control system is self-learning in that at least some of the initial and subsequent parameters of the system are determined automatically during runtime.