M. Abul Masrur

Battery state of charge estimation based on a combined model of Extended Kalman Filter and neural networks

This paper presents our research in battery State of Charge (SOC) estimation for intelligent battery management. Our research focus is to investigate online dynamic SOC estimation using a combination of Kalman filtering and a neural network. First, we developed a method to model battery hysteresis effects using Extended Kalman Filter (EKF). Secondly, we designed a SOC estimation model, NN-EKF model, that incorporates the estimation made by the EKF into a neural network. The proposed methods have been evaluated using real data acquired from two different batteries, a lithium-ion battery U1-12XP and a NiMH battery with 1.2V and 3.4 Ah. Our experiments show that our EKF method developed to model battery hysteresis based on separated charge and discharge Open Circuit Voltage (OCV) curves gave the top performances in estimating SOC when compared with other advanced methods. Secondly, the NN-EKF model for SOC estimation gave the best SOC estimation with and without temperature data.

Battery hysteresis modeling for state of charge estimation based on Extended Kalman Filter

This paper presents our research in battery SOC estimation for intelligent battery management. We developed a SOC estimation algorithm based on Extended Kalman Filter to model battery hysteresis effects. The proposed method has been evaluated using data acquired from two different batteries, a lithium-ion battery U1–12XP and a NiMH battery with 1.2V and 3.4 Ah. Our experiments show that our method, which models battery hysteresis based on separated charge and discharge OCV curves gave the top performances in estimating SOC in both batteries when compared with other advanced methods.

Neural learning of driving environment prediction for vehicle power management

Vehicle power management has been an active research area in the past decade, and has intensified recently by the emergence of hybrid electric vehicle technologies. Research has shown that driving style and environment have strong influence over fuel consumption and emissions. In order to incorporate this type of knowledge into vehicle power management, an intelligent system has to be developed to predict the current traffic conditions. This paper presents our research in neural learning for predicting the driving environment such as road types and traffic congestions. We developed a prediction model, an effective set of features to characterize different types of roadways, and a neural network trained for online prediction of roadway types and traffic congestion levels. This prediction model was then used in conjunction with a power management strategy in a conventional (non-hybrid) vehicle. The benefits of having the predicted drive cycle available are demonstrated through simulation.

Intelligent vehicle power management using machine learning and fuzzy logic

We present our research in optimal power management for a generic vehicle power system that has multiple power sources using machine learning and fuzzy logic. A machine learning algorithm, LOPPS, has been developed to learn about optimal power source combinations with respect to minimum power loss for all possible load requests and various system power states. The results generated by the LOPPS are used to build a fuzzy power controller (FPC). FPC is integrated into a simulation program implemented by using a generic simulation software as indicated in reference and is used to dynamically allocate optimal power sources during online drive. The simulation results generated by FPC show that the proposed machine learning algorithm combined with fuzzy logic is a promising technology for vehicle power management.

Special Section on Condition Monitoring and Fault Accommodation in Electric and Hybrid Propulsion Systems

The six papers in this special section focus on the state-of-the art research and development of diagnosis and fault-tolerant control in electric and hybrid propulsion systems.

Distributed Heterogeneous Simulation of a Hybrid-Electric Vehicle Drive System Using the Simplorer Software Product

Hybrid-electric military vehicles provide many advantages over conventional military vehicles powered solely by diesel or turbine engines. These advantages include improved acceleration and fuel economy, stealth capability for silent mobility and silent watch, and ability to carry future energy weapons and advanced armor protection. The U.S. Army Research, Development and Engineering Command (RDECOM) and Tank Automotive Research, Development and Engineering Center (T ARDEC) have sponsored the modeling and distributed simulation of a hybrid-electric vehicle as a design and validation tool for the development of future military vehicles. This paper describes the structure of the electricaVpropuls,ion system of the vehicle, and the modeling of the components within this system. In particular, modeling of the prime mover (a diesel engine), the generator/motor, the vehicle control system, and other major components are discussed. Distributed simulation was accomplished using the Distributed Heterogeneous Simulation (DHS) tool. Specifically, the model of the system was divided into multiple subsystems, whereupon DHS was used to connect the subsystem models to form a synchronized simulation, which can be executed on one computer or multiple networked computers. In addition to increasing simulation speed, DHS also anows the interconnection between component models developed in different simulation languages, without requiring them to be translated into a common language. This advantage is particularly important if component models developed in other languages, likely from component manufacturers, are to be added to the vehicle model in the future. The performance of the vehicle system was evaluated under various operating conditions, and simulation results demonstrating the behavior of the system are presented.

Intelligent Energy Management in a Low Cost Hybrid Electric Vehicle Power System

This paper presents our research in vehicle energy optimization for a low-cost HEV power system that only allows the control of engine on/off and driving at three different speed limits. We present algorithms for modeling vehicle energy flow and optimization and machine learning of optimal control settings generated by Dynamic Programming on real-world drive cycles, and an intelligent energy controller designed for online energy control. Experimental results show the intelligent controller has the capability of 11% fuel saving.

Fault diagnostics in electric drives using machine learning

Electric motor and power electronics based inverter are the major components in industrial and automotive electric drives. In this paper we present a fault diagnostics system developed using machine learning technology for detecting and locating multiple classes of faults in an electric drive. A machine learning algorithm has been developed to automatically select a set of representative operating points in the (torque, speed) domain, which in turn is sent to the simulated electric drive model to generate signals for the training of a diagnostic neural network, “Fault Diagnostic Neural Network” (FDNN). We presented our study on two different neural network systems and show that a well-designed hierarchical neural network system is robust in detecting and locating faults in electric drives.

Distributed Heterogeneous Simulation of a Hybrid-Electric Vehicle

Abstract : Hybrid-electric military vehicles provide many advantages over conventional military vehicles powered solely by diesel or turbine engines. These advantages include improved acceleration and fuel economy, stealth capability for silent mobility and silent watch, and ability to carry future energy weapons and advanced armor protection. The U.S. Army Research, Development and Engineering Command (RDECOM) and Tank Automotive Research, Development and Engineering Center (TARDEC) have sponsored the modeling and distributed simulation of a hybrid-electric vehicle as a design and validation tool for the development of future military vehicles. This paper describes the structure of the electrical/propulsion system of the vehicle, and the modeling of the components within this system. In particular, modeling of the prime mover (a diesel engine), the generator/motor the vehicle control system, and other major components are discussed. Distributed simulation was accomplished using the Distributed Heterogeneous Simulation (DHS) tool. Specifically, the model of the system was divided into multiple subsystems, whereupon DHS was used to connect the subsystem models to form a synchronized simulation, which can be executed on one computer or multiple networked computers. In addition to increasing simulation speed, DHS also allows the interconnection between component models developed in different simulation languages, without requiring them to be translated into a common language. This advantage is particularly important if component models developed in other languages, likely from component manufacturers, are to be added to the vehicle model in the future. The performance of the vehicle system was evaluated under various operating conditions, and simulation results demonstrating the behavior of the system are presented.

Intelligent Energy Management and Optimization in a Hybridized All-Terrain Vehicle With Simple On–Off Control of the Internal Combustion Engine

This paper presents research in cognitive vehicle energy management for low-cost hybrid electric vehicle (HEV) power systems for small vehicles, such as all-terrain vehicles (ATVs). The power system consists of a small engine, a lead-acid battery, and an ultracapacitor. For simplicity of implementation and low hardware cost, engine control is restricted to two states, i.e., on and off, and vehicle speed control is restricted to three discrete levels, namely, high, medium, and low. The authors developed advanced algorithms for modeling and optimizing vehicle energy flow, machine learning of optimal control settings generated by dynamic programmling on real-world drive cycles, and an intelligent energy controller designed for online energy control based on knowledge about the driving mission and knowledge obtained through machine learning. The intelligent vehicle energy controller cognitive intelligent power management (CIPM) has been implemented and evaluated in a simulated vehicle model and in an ATV, i.e., Polaris Ranger EV, which was converted to an HEV. Experimental results show that the intelligent energy controller CIPM can lead to a significant improvement in fuel economy compared with the existing conventional vehicle controllers in an ATV.