Related Experiment Video
Updated: Aug 22, 2025

Author Spotlight: Simulation and Analysis of the Temperature Rise of Ring Main Unit Equipment
Published on: July 5, 2024
Machine Learning and Swarm Optimization Algorithm in Temperature Compensation of Pressure Sensors
Hexing Wang1,2, Jia Li1,2
1Institute of Microelectronics of the Chinese Academy of Sciences, Beijing 100029, China.
This study introduces novel temperature compensation methods for MEMS piezoresistive pressure sensors using swarm optimization and machine learning. Optimized algorithms significantly enhance sensor accuracy across different operating ranges.
Area of Science:
- Sensor Technology
- Machine Learning
- Optimization Algorithms
Background:
- MEMS piezoresistive pressure sensors require accurate temperature compensation for reliable performance.
- Existing software compensation methods often lack sensor-specific range optimization and disregard operating characteristics.
- Developing tailored compensation algorithms is crucial for improving sensor output accuracy.
Purpose of the Study:
- To propose and evaluate novel temperature compensation methods for MEMS piezoresistive pressure sensors.
- To investigate the effectiveness of swarm optimization algorithms fused with machine learning for different sensor ranges.
- To determine the optimal calibration dataset partitioning ratio for enhanced compensation performance.
Main Methods:
- Development of three temperature compensation algorithms integrating swarm optimization and machine learning.
- Application of algorithms to MEMS piezoresistive pressure sensors across distinct operational ranges.
- Experimental analysis of calibration dataset partitioning ratios on Sensor A performance.
- Comparative evaluation against existing state-of-the-art compensation algorithms.
Main Results:
- Different swarm optimization and machine learning algorithms demonstrated suitability for specific pressure sensor ranges.
- Optimal temperature compensation on Sensor A was achieved with a 33.3% data split ratio.
- Achieved zero-drift coefficient of 2.88 × 10-7/°C and sensitivity temperature coefficient of 4.52 × 10-6/°C.
- Proposed algorithms outperformed existing methods in literature.
Conclusions:
- Swarm optimization and machine learning fusion offers a powerful approach for MEMS pressure sensor temperature compensation.
- Sensor-specific range optimization and calibration data partitioning are critical for maximizing compensation effectiveness.
- The findings provide a significant advancement in achieving high-accuracy MEMS pressure sensing.
More Related Videos
10:36Author Spotlight: Optimization of Airflow Velocities in Battery Cooling Systems for Enhanced Thermal Performance and Reduced Energy Consumption
Published on: November 3, 2023
06:45Design and Application of a Fault Detection Method Based on Adaptive Filters and Rotational Speed Estimation for an Electro-Hydrostatic Actuator
Published on: October 28, 2022
Related Concept Videos
Thermal expansion and Thermal stress: Problem Solving
To solve the problem, first, identify the known and unknown quantities. The initial length (L) of the bridge is 1275 m, the coefficient of linear expansion (α) for steel is 12 x 10-6/°C, and the change in...
Measurement of Fluid Pressure
A basic form of manometer is the piezometer, a vertical tube open at the top and filled with the same...
Temperature Measurement Sites
Oral: When assessing oral temperature, the thermometer tip should be placed under the tongue in the posterior sublingual pocket. It offers accurate readings and can be...
Constant Pressure Calorimetry
Temperature and Thermal Equilibrium
The concept of temperature has evolved from the common concepts of hot and cold. The scientific definition of temperature explains more than just our sense of hot and cold. Temperature is operationally defined as the quantity measured with a thermometer. Furthermore, temperature is...
PID Controller