Toe misalignment is frequently encountered in Heavy Commercial Road Vehicles (HCRVs). Over
50% of trucks reported measurable toe misalignment in their early life. Wheel misalignment
detection and its correction are important periodic tasks recommended by Original Equipment
Manufacturers (OEMs) for HCRVs. This aids in preventing misalignment related premature tyre
wear, resulting microplastic emissions and improves fuel economy. Existing misalignment
detection methods require manual intervention, causing truck downtime. A few studies used the
rule-based method, while some used the data-driven method to detect toe misalignment in an
autonomous truck with the Advanced Driver Assistance System (ADAS). These studies did not
propose a data-driven method to detect toe misalignment in an HCRV that did not require ADAS
functionality. The objective of this study was to evaluate the effectiveness of the data-driven
method to accurately detect toe and thrust misalignment in the single-unit twin-axle HCRVs in real
time with reasonable precision and fewer false alarms. This study proposed to develop an onboard
solution that continuously monitors data in real-time from the Inertial Measurement Unit, Global
Positioning System, wheel speed and steering wheel angle sensors to automatically detect
misalignment to prevent misalignment-related issues. Two ramp steer manoeuvres for symmetric
and asymmetric toe configurations were simulated in IPG TruckMaker®, a vehicle dynamics
simulation software. The Support Vector Classifier model was trained and evaluated on the
simulated data for the lateral acceleration of sprung mass, longitudinal velocity, four-wheel speed,
steering wheel angle and vehicle yaw rate. The data-driven method indicated better effectiveness
in detecting symmetric toe misalignment with fewer false alarmsfor both ramp manoeuvres when
compared with asymmetric toe misalignment. The outcomes of this study are expected to
contribute towards an onboard automated wheel misalignment detection solution in HCRVs to
alert drivers of toe and thrust misalignments in real-time.