When More Modalities Hurt: Modality Dropout for Heavy-Duty Vehicle Engine Diagnostics
2026-08-24 • Machine Learning
Machine Learning
AI summaryⓘ
The authors studied how combining three different types of data—text service complaints, sensor data, and fault codes—can improve identifying problems in heavy-duty vehicle engines. They found that simply mixing these data types helps a little, but purposely training the model to rely on weaker data sources boosts performance more. Different data types work better for different engine faults; for example, sensors are particularly good at identifying intake and exhaust problems. Their approach is the first to combine these three data types for vehicle diagnostics and shows promising improvements.
heavy-duty vehiclesdiagnosticsmultimodal fusionsensor telemetryDiagnostic Trouble Codes (DTCs)text miningmachine learningmodality dropoutengine fault classification
Authors
Adeel Zafar, Slawomir Nowaczyk, Hamid Sarmadi, Saeed Gholami Shahbandi
Abstract
Heavy-duty vehicle diagnostics generate three disconnected data modalities: unstructured multi- lingual service complaints, high-dimensional sensor telemetry with over 80% missing values, and Diagnostic Trouble Codes (DTCs). We investigate whether fusing these modalities improves engine component classification on a proprietary dataset from a major truck manufacturer. Through 5-fold cross-validation across multiple model configurations spanning three model families on five engine component classes (885 samples, the full cross-database matched population for this manufacturer), we find that naive fusion provides modest gains over text alone (65.3%). However, modality dropout during training, which randomly disables entire modalities per batch, forces the network to exploit weaker inputs and achieves 68.8% accuracy on text+DTC fusion (weighted F1: 0.67), a 3.5-point improvement over text-only (65.3%, weighted F1: 0.64) and the best result across all methods including logistic regression and gradient-boosted trees. Per-class analysis shows that the dominant modality varies by fault type: text describes symptoms, DTCs encode structured fault signals, and sensors measure physical state. On intake/exhaust faults, sensors alone reach 93% where text achieves 80%. On fuel system faults, fusion with modality dropout nearly triples accuracy from 15% to 38% over text alone. To our knowledge, this is the first application of three-way modality fusion combining text, sensors, and fault codes in industrial vehicle diagnostics.