Accurate Measurement of Blast Shock Wave Pressure by Enhanced Sensor System Based on Neural Network

Area of Science:

• Mechanical Engineering
• Sensor Technology
• Signal Processing

Background:

• Blast shock wave pressure measurement is susceptible to errors from mechanical vibrations and shocks.
• Existing sensors struggle with dynamic characteristics during transient pressure rises, impacting accuracy.
• Improving measurement precision during the compression phase is critical for accurate blast analysis.

Purpose of the Study:

• To enhance the dynamic response of shock wave pressure sensors for improved accuracy.
• To investigate the impact of a novel buffer device on sensor performance.
• To develop and implement a dynamic compensation method using a backpropagation neural network.

Main Methods:

• Designed a specialized buffer device to improve sensor response to transient pressure.
• Conducted dynamic calibration of the enhanced sensor system using a double-diaphragm shock tube.
• Developed a backpropagation (BP) neural network model for sensor system characterization and dynamic compensation.

Main Results:

• The buffer device reduced the operational bandwidth of the sensor system.
• BP neural network-based dynamic compensation effectively widened the bandwidth.
• Measurement accuracy of the enhanced shock wave pressure sensor system was significantly improved.

Conclusions:

• The combined buffer device and BP neural network compensation offer a practical solution for high-precision dynamic pressure measurement.
• This approach is particularly effective for the compression phase in challenging environments.
• The research advances capabilities in accurate transient pressure sensing technology.