Enhanced algorithm for predictive maintenance to detect turbocharger overspeed in diesel engine rail vehicles

Area of Science:

• Mechanical Engineering
• Railway Engineering
• Condition Monitoring

Background:

• Locomotive reliability and safety are paramount for efficient train operations.
• Repeated turbocharger failures in locomotive fleets pose significant safety risks.
• Failures are preceded by uncontrolled acceleration and overspeed transients of the turbocharger shaft.

Purpose of the Study:

• To present an enhanced novel algorithm for estimating Instantaneous Angular Speed (IAS) of turbochargers and diesel engines.
• To overcome challenges posed by transient operating conditions in diesel engines.
• To enable early detection of potential turbocharger failures by predicting overspeed conditions.

Main Methods:

• Developed an enhanced algorithm using adaptive dephasing to estimate IAS.
• The algorithm isolates critical asynchronous vibration components for failure detection.
• It is suitable for non-stationary speeds and various rotational speeds/rates of change.

Main Results:

• The algorithm effectively estimates IAS under transient conditions.
• It successfully isolates critical vibration components for early failure detection.
• The method correlates characteristic frequencies of rotating parts for robustness.

Conclusions:

• The novel IAS estimation algorithm enhances predictive maintenance and operational reliability of locomotives.
• It is specifically designed for diesel engine operating conditions.
• Validation with simulated and experimental data confirms the algorithm's effectiveness and robustness.