Mark N. Howell

Data-driven fault diagnosis in a hybrid electric vehicle regenerative braking system

Regenerative braking is one of the most promising and environmentally friendly technologies used in electric and hybrid electric vehicles to improve energy efficiency and vehicle stability. In this paper, we discuss a systematic data-driven process for detecting and diagnosing faults in the regenerative braking system of hybrid electric vehicles. The process involves data reduction techniques, exemplified by multi-way partial least squares, multi-way principal component analysis, for implementation in memory-constrained electronic control units and well-known fault classification techniques based on reduced data, such as support vector machines, k-nearest neighbor, partial least squares, principal component analysis and probabilistic neural network, to isolate faults in the braking system. The results demonstrate that highly accurate fault diagnosis is possible with the pattern recognition-based techniques. The process can be employed for fault analysis in a wide variety of systems, ranging from automobiles to buildings to aerospace systems.

Integrated model-based and data-driven fault detection and diagnosis approach for an automotive electric power steering system

Integrity of electric power steering system is vital to vehicle handling and driving performance. Advances in electric power steering (EPS) system have increased complexity in detecting and isolating faults. In this paper, we propose a hybrid model-based and data-driven approach to fault detection and diagnosis (FDD) in an EPS system. We develop a physics-based model of an EPS system, conduct fault injection experiments to derive fault-sensor measurement dependencies, and investigate various FDD schemes to detect and isolate the faults. Finally, we use an SVM regression technique to estimate the severity of faults.

Fault Diagnosis in Hybrid Electric Vehicle Regenerative Braking System

Regenerative braking is one of the most promising and environmentally friendly technologies used in electric and hybrid electric vehicles to improve energy efficiency and vehicle stability. This paper presents a systematic data-driven process for detecting and diagnosing faults in the regenerative braking system of hybrid electric vehicles. The diagnostic process involves signal processing and statistical techniques for feature extraction, data reduction for implementation in memory-constrained electronic control units, and variety of fault classification methodologies to isolate faults in the regenerative braking system. The results demonstrate that highly accurate fault diagnosis is possible with the classification methodologies. The process can be employed for fault analysis in a wide variety of systems, ranging from automobiles to buildings to aerospace systems.

Multiple model moving horizon estimation approach to prognostics in coupled systems

The key objectives of this paper are to analyze and implement a novel moving horizon model predictive estimation scheme based on constrained nonlinear optimization techniques for inferring the survival functions and residual useful life (RUL) of components in coupled systems. The approach employs a data-driven prognostics framework that combines failure time data, static and dynamic (time-series) parametric data, and the Multiple Model Moving Horizon Estimation (MM-MHE) algorithm for predicting the survival functions of components based on their usage profiles. Validation of the approach has been provided based on data from an electronic throttle control (ETC) system. The proposed prognostic approach is modular and has the potential to be applicable to a wide variety of systems, ranging from automobiles to aerospace.