Accurate fault diagnosis in air brake is crucial to reduce frequent brake inspection and maintenance in heavy commercial road vehicles. Existing model-based fault diagnostic schemes work well under limited vehicle operating conditions, which is insufficient for developing an on-board monitoring device. In this context, a learning-based fault identification scheme using the Random Forest technique, which accommodates the vehicle’s wide operating conditions, is proposed. This scheme identifies the brake’s fault levels with a better classification accuracy of 92% compared to techniques such as Naïve Bayes, k-Nearest Neighbors, Support Vector Machine, and Decision Tree. Further, a fault-tolerant controller is proposed to overcome the vehicle’s directional instability arising due to the brake fault. Two sliding mode controllers, namely differential brake control and steering angle control, were developed to control the yaw angle. These have been implemented in a Hardware in Loop experimental platform with the vehicle dynamic simulation software TruckMaker®.
This paper presents a string stable controller for the autonomous operation of a platoon of Heavy Commercial Road Vehicles (HCRVs) in a connected environment. This study considers factors such as brake/powertrain actuator dynamics, resistive forces, tyre model and wheel dynamics, which are crucial during on-road operation of HCRVs. A nonlinear vehicle dynamic model encompassing all these factors has been considered. The dependency between aerodynamic drag and inter-vehicular distance in the platoon has also been taken into account. The aforementioned factors motivated the use of Sliding Mode Control (SMC), which is a nonlinear and robust control technique. A lower level Proportional Integral Derivative (PID) controller has been successfully integrated with SMC to compensate for pneumatic brake and powertrain system delay. The designed controller was evaluated for string stable platoon operation by considering various road conditions, load conditions and operating speeds. It was observed that the string stable controller performance is highly dependent on the operating conditions. To ensure string stable operation for different operating scenarios, an adaptive time-headway based enhancement has also been integrated in the controller design. The efficacy of the proposed adaptive time-headway policy over the existing constant time-headway policy has been methodically analysed and a performance comparison between them has also been presented. The aspect of communication delay during connected vehicular operation has also been studied and the maximum tolerable communication delay magnitude for maintaining string stable operation has also been presented.
1 August 2018 in Journal of the Franklin Institute
This work provides a model-based approach to develop a wheel slip regulation scheme for Antilock Braking System (ABS) in Heavy Commercial Road Vehicles (HCRVs). Physical constraints of the actuator in the pneumatic brake system such as operating bandwidth and delay were considered in the design. The slip regulation scheme was designed using Power Rate Exponential Reaching Law (PRERL) based Sliding Mode Controller (SMC), which is a new strategy employed for ABS application. This technique consists of both chattering mitigation and robustness properties. Additionally, the effect of actuator delay on performance deterioration of the slip regulator was studied and an appropriate method was developed to mitigate it. The complete design was evaluated in a Hardware-in-Loop (HiL) experimental setup for several cases of road and load conditions and seen to regulate slip fairly accurately with an average tracking error of . Further, the stopping distance reduction was up to with the controller. The developed algorithm was found to be robust to of mass variations and of road surface variations.