The air pressure system (APS) plays a prime role in pressurizing various subsystems of heavy-duty vehicles (HVDs). However, its reliability is crucial to ensure uninterrupted operation where failures in APS lead to HVDs being stranded on the road with the manufacturers and operators incurring associated high costs. This paper addresses the problem of predicting failures in APS using a semi-supervised transformer-based framework. The proposed framework commences with important preprocessing steps including data segmentation followed by sliding windows to handle the big raw data, and subsequent extraction of distinctive features. Using these features, the transformer model was trained to reconstruct data from healthy vehicles (i.e., vehicles without any APS failures) to capture the normal behavior of the healthy vehicles. At inference, the trained model distinguished the faulty vehicles with detected APS failure from the healthy ones based on their reconstruction errors. This semi-supervised formulation of APS failure detection overcomes limitations such as the imbalanced data issue and anomaly heterogeneity that are associated with the conventional supervised formulation. The model demonstrated robust performance with an F1 score of approximately 0.76, an accuracy of about 85%, and a high recall of 0.833, indicating successful detection of most faulty vehicles. Such advancements promise significant improvements in vehicle diagnostics and predictive maintenance.

In this paper, a machine learning (ML) system is introduced to detect high fuel consumption in heavy-duty vehicles (HDVs) using operational data. The system addresses environmental and efficiency challenges in the transportation industry by precisely monitoring fuel consumption to curb CO2 emissions. An ensemble learning method that integrates unsupervised anomaly detection techniques, including Isolation Forest, Autoencoder, and k-NN Regressor models, is proposed. The anomaly detection results from these models are combined using a weighted majority voting (WMV) approach. This method was tested on a dataset comprising 459 driving records and 14 signals collected from 187 HDVs. Additionally, the Local Outlier Factor (LOF) model was employed to validate the ensemble learning method and investigate the factors contributing to the anomalies. This work enhances transportation efficiency by offering a novel approach for analyzing fuel consumption in HDVs, thereby paving the way for future advancements in sustainable transportation practices.

In this paper, a fault tolerant control system for a quadrotor helicopter is developed. Fault tolerant controllers have many advantages over regular controllers for keeping midair flight safety and increasing mission reliability. A high-fidelity nonlinear model of a quadrotor is constructed using Newton-Euler formulation where Dryden wind effects and sensor noise are included to simulate real-world fight conditions. For managing accurate full state estimations, an Extended Kalman Filter is utilized. To increase robustness to external disturbances and uncertainties in the plant dynamics, a Velocity-based Disturbance Observer (VbDOB) is constructed and combined with the control law. Simulations carried out with the high fidelity model have shown that the proposed method has successfully compensated for actuator faults in a trajectory tracking task, and hence provides good tracking performance with a feasible control effort.

In this paper, we present a real-time driver evaluation system for heavy-duty vehicles by focusing on the classification of risky acceleration and braking behaviors. We utilize an improved version of our previous Long Short Memory (LSTM) based acceleration behavior model [10] to evaluate varying acceleration behaviors of a truck driver in small time periods. This model continuously classifies a driver as one of six driver classes with specified longitudinal-lateral aggression levels, using driving signals as time-series inputs. The driver gets acceleration score updates based on assigned classes and the geometry of driven road sections. To evaluate the braking behaviors of a truck driver, we propose a braking behavior model, which uses a novel approach to analyze deceleration patterns formed during brake operations. The braking score of a driver is updated for each brake event based on the pattern, magnitude, and frequency evaluations. The proposed driver evaluation system has achieved significant results in both the classification and evaluation of acceleration and braking behaviors.