Monitoring

Monitoring

BIC is conducting industrially oriented research on novel and traditional sensing technologies along with condition monitoring techniques enabled by Internet of Things (IoT).

BIC’s specialists are delivering leading-edge monitoring technologies for Structural Health Monitoring (SHM) and Condition Monitoring (CM) applications i.e. ultrasonic guided waves, acoustic emission and vibration analysis. BIC has wide range of sensing hardware ranging from IEPE sensors to MEMS sensors to FBF sensors for specific applications (ATEX, electromagnetic compatibility, etc.). Beyond implementing the appropriate sensing techniques, the centre is implementing advanced analytics combining signal processing techniques for extracting damage sensitive features hidden in time signals and machine learning techniques for automated defect detection and classification. This automation facilitates routine maintenance to ensure the healthy states of structures and improves cost efficiency.

BIC’s monitoring solutions could be applied in various markets; aerospace, oil and gas, renewables and manufacturing.

CORE AREAS OF RESEARCH

Condition and Structural health monitoring
Piezoelectric and Electromagnetic sensors
Hardware design and testing
Digital Signal Processing
Internet of Things (IoT)
Machine Learning
Digital Twin

KEY PROJECTS

OPTRAIL

BIC developed a novel signal processing toolbox for real time monitoring of track bed voids based on Fibre Optic (FO) sensor data. Fibre Optic Rail Asset Monitoring System (FRAMS) capable of providing train traffic information, along with track-sleeper assembly degradation indication is demonstrated at London DLR popular track.

DIMOS

SMARTBRIDGE

The SmartBridge (intelligent bridge health monitoring application) project has established an automated Structural Health Monitoring application that would send out alerts upon detection of defects. This has enhanced the efficiency to save cost on early defect maintenance and also aids in maintenance scheduling. IoT sensors such as temperature, stress and vibration sensors were installed on the MR76 bridge (owned by London Underground - pictured). BIC has developed signal processing algorithms to detect abnormal event anomaly and extract modal analysis features automatically. The extracted features will then be used as input for the machine learning model to monitor the health status of the bridge.