Search Results

This research proposes a control system for Spark Ignition (SI) engines with external Exhaust Gas Recirculation (EGR) based on model predictive control and a disturbance observer. The proposed Economic Nonlinear Model Predictive Controller (E-NMPC) tries to minimize fuel consumption for a number of engine cycles into the future given an Indicated Mean Effective Pressure (IMEP) tracking reference and abnormal combustion constraints like knock and combustion variability. A nonlinear optimization problem is formulated and solved in real time using Sequential Quadratic Programming (SQP) to obtain the desired control actuator set-points. An Extended Kalman Filter (EKF) based observer is applied to estimate engine states, combining both air path and cylinder dynamics. The EKF engine state(s) observer is augmented with disturbance estimation to account for modeling errors and/or sensor/actuator offset.

This paper outlines a real-time hierarchical control allocation algorithm for multi-axle land vehicles with independent hub motor wheel drives. At the top level, the driver’s input such as pedal position or steering wheel position are interpreted into desired global state responses based on a reference model. Then, a locally linearized rigid body model is used to design a linear quadratic regulator that generates the desired global control efforts, i.e., the total tire forces and moments required track the desired state responses. At the lower level, an optimal control allocation algorithm coordinates the motor torques in such a manner that the forces generated at tire-road contacts produce the desired global control efforts under some physical constraints of the actuation and the tire/wheel dynamics. The performance of the proposed control system design is verified via simulation analysis of a 3-axle heavy vehicle with independent hub-motor drives.

This study investigates the use of machine learning methods for the selection of energy storage devices in military electrified vehicles. Powertrain electrification relies on proper selection of energy storage devices, in terms of chemistry, size, energy density, and power density, etc. Military vehicles largely vary in terms of weight, acceleration requirements, operating road environment, mission, etc. This study aims to assist the energy storage device selection for military vehicles using the data-drive approach. We use Machine Learning models to extract relationships between vehicle characteristics and requirements and the corresponding energy storage devices. After the training, the machine learning models can predict the ideal energy storage devices given the target vehicles design parameters as inputs. The predicted ideal energy storage devices can be treated as the initial design and modifications to that are made based on the validation results.

Vehicle safety remains a significant concern for consumers, government agencies, and automotive manufacturers. One critical type of vehicle accident results from the right or left side tires leaving the road surface and then returning abruptly due to large steering wheel inputs (road runoff and return). A subset of runoff road crashes that involve a steep hard shoulder has been labeled shoulder induced accidents. In this paper, a limited authority real time steering controller has been developed to mitigate shoulder induced accidents. A Kalman Filter based tire cornering stiffness estimation technique has been coupled with a feedback controller and driver intention module to create a safer driving solution without excessive intervention. In numerical studies, lateral vehicle motion improvements of 30% were realized for steering intervention. Specifically, the vehicle crossed the centerline after 1.0 second in the baseline case versus 1.3 seconds with steering assistance at 60 kph.

The emphasis on vehicle fuel economy and tailpipe emissions, coupled with a trend toward greater system functionally, has prompted automotive engineers to develop on-board control systems with increased requirements and complexity. Mainstream engine controllers regulate fuel, spark, and other subsystems using custom solutions that incorporate off-the-shelf hardware components. Although the digital processor core and the peripheral electronics may be similar, these controllers are targeted to fixed engine architectures which limit their flexibility across vehicle platforms. Moreover, additional software needs are emerging as electronics continue to permeate the ground transportation sector. Thus, automotive controllers will be required to assume increased responsibility while effectively communicating with distributed hardware modules.

Low-pressure cooled EGR (LP-cEGR) systems can provide significant improvements in spark-ignition engine efficiency and knock resistance. However, open-loop control of these systems is challenging due to low pressure differentials and the presence of pulsating flow at the EGR valve. This research describes a control structure for Low-pressure cooled EGR systems using closed loop feedback control along with internal model control. A Smith Predictor based PID controller is utilized in combination with an intake oxygen sensor for feedback control of EGR fraction. Gas transport delays are considered as dead-time delays and a Smith Predictor is one of the conventional methods to address stability concerns of such systems. However, this approach requires a plant model of the air-path from the EGR valve to the sensor.

In this paper, a reinforcement learning-based method is proposed to adapt autonomous vehicle passengers’ expectation of comfort through in-situ human-vehicle interaction. Ride comfort has a significant influence on the user’s experience and thus acceptance of autonomous vehicles. There is plenty of research about the motion planning and control of autonomous vehicles. However, limited studies have explicitly considered the comfort of passengers in autonomous vehicles. This paper studies the comfort of humans in autonomous vehicles longitudinal autonomous driving. The paper models and then improves passengers’ feelings about autonomous driving behaviors. This proposed approach builds a control and adaptation strategy based on reinforcement learning using human’s in-situ feedback on autonomous driving. It also proposes an adaptation of humans to autonomous vehicles to account for improper human driving expectations.

Modeling and simulation of ground vehicles can be a computationally expensive problem due to the complexity of high-fidelity vehicle models. Often to determine mobility metrics, multiple stochastic simulations need to be evaluated. Surrogate models, or models of models, offer a means to reduce the computational cost of these simulation efforts. Since various types of surrogate models are available to the user, choosing the best surrogate model for a simulation is mostly the challenging process. In this paper, the process of selecting surrogate models and its uses based on model metafeatures is presented. The approach formulates this decision as a trade-off among three main drivers, required dataset size (how much information is necessary to compute the surrogate model), surrogate model accuracy (how accurate the surrogate model must be) and total computational time (how much time is required for the surrogate modeling process).

Integrated modeling of vehicle, tire and terrain is a fundamental challenge to be addressed for off-road autonomous navigation. The complexities arise due to lack of tools and techniques to predict the continuously varying terrain and environmental conditions and the resultant non-linearities. The solution to this challenge can now be found in the plethora of data driven modeling and control techniques that have gained traction in the last decade. Data driven modeling and control techniques rely on the system’s repeated interaction with the environment to generate a lot of data and then use a function approximator to fit a model for the physical system with the data. Getting good quality and quantity of data may involve extensive experimentation with the physical system impacting developer’s resource. The process is computationally expensive, and the overhead time required is high.

The application of virtual engineering methods can streamline the product design process through improved collaboration opportunities among the technical staff and facilitate additive manufacturing processes. A product digital twin can be created using the available computer-aided design and analytical mathematical models to numerically explore the current and future system performance based on operating cycles. The strategic decision to implement a digital twin is of interest to companies, whether the required financial and workforce resources will be worthwhile. In this paper, two metrics are introduced to assist management teams in evaluating the technology potential. The usefulness and time savings metrics will be presented with accompanying definitions. A case study highlights the usefulness metric for the “Deep Orange” prototype vehicle, an innovative off-road hybrid vehicle designed and fabricated at Clemson University.

Autonomous vehicles (AV) are sophisticated systems comprising various sensors, powerful processors, and complex data processing algorithms that navigate autonomously to their respective goals. Out of several functions performed by an AV, one of the most important is developing situational intelligence to predict collision-free future trajectories. As an AV operates in environments consisting of various entities, such as other AVs, human-driven vehicles, and static obstacles, developing situational intelligence will require a collaborative approach. The recent developments in artificial intelligence (AI) and deep learning (DL) relating to AVs have shown that DL-based models can take advantage of information sharing and collaboration to develop such intelligence.

This paper details the concept of using an exergy-based method as a thermal design methodology tool for integrated aircraft thermal systems. An exergy-based approach was applied to the design of an environmental control system (ECS) of an advanced aircraft. Concurrently, a traditional energy-based approach was applied to the same system. Simplified analytical models of the ECS were developed for each method and compared to determine the validity of using the exergy approach to facilitate the design process in optimizing the overall system for a minimum gross takeoff weight (GTW). The study identified some roadblocks to assessing the value of using an exergy-based approach. Energy and exergy methods seek answers to somewhat different questions making direct comparisons awkward. Also, high entropy generating devices can dominate the design objective of the exergy approach.

Learning only from a small set of examples remains a huge challenge in machine learning. Despite recent breakthroughs in the applications of neural networks, the applicability of these techniques has been limited by the requirement for large amounts of training data. What’s more, the standard supervised machine learning method does not provide a satisfactory solution for learning new concepts from little data. However, the ability to learn enough information from few samples has been demonstrated in humans. This suggests that humans may make use of prior knowledge of a previously learned model when learning new ones on a small amount of training examples. In the area of autonomous driving, the model learns to drive the vehicle with training data from humans, and most machine learning based control algorithms require training on very large datasets. Collecting and constructing training data set takes a huge amount of time and needs specific knowledge to gather relevant information.

This paper aims to present an enhanced fuzzy sliding-mode control scheme with variable rate reaching law for semi-active vehicle suspension systems, which can reduce chattering phenomena in high frequency compared with the sliding-mode controller with traditional exponent reaching law. First, an ideal-skyhook damping suspension system is taken as reference model; then the new control law is synthesized by employing the fuzzy logic control while considering the sliding-mode reaching segment characteristics, which can dynamically change the reaching rate to suppress chattering in closed-loop control systems; finally, simulation analysis is conducted under both random road and bump road surface, the results verified the effectiveness and feasibility of the proposed control scheme.

Recent trends in autonomy have emphasized end-to-end deep-learning-based methods that have shown a lot of promise in overcoming the requirements and limitations of feature-engineering. However, while promising, the black-box nature of deep-learning frameworks now exacerbates the need for testing with end-to-end deployments. Further, as exemplars of systems-of-systems, autonomous vehicles (AVs) engender numerous interconnected component-, subsystem and system-level interactions. The ensuing complexity creates challenges for verification and validation at the various component, subsystem- and system-levels as well as end-to-end testing. While simulation-based testing is one promising avenue, oftentimes the lack of adequate fidelity of AV and environmental modeling limits the generalizability. In contrast, full-scale AV testing presents the usual limitations of time-, space-, and cost.

Non-linear model predictive engine control (nMPC) systems have the ability to reduce calibration effort while improving transient engine response. The main drawback of nMPC for engine control is the computational power required to realize real-time operation. Most of this computational power is spent linearizing the non-linear plant model at each time step. Additionally, the effectiveness of the nMPC system relies heavily on the accuracy of the model(s) used to predict the future system behavior, which can be difficult to model physically. This paper introduces a hybrid modeling approach for internal combustion engines that combines physics-based and machine learning techniques to generate accurate models that can be linearized with low computational power. This approach preserves the generalization and robustness of physics-based models, while maintaining high accuracy of data-driven models. Advantages of applying the proposed model with nMPC are discussed.

Knock control systems are fundamentally stochastic, regulating some aspect of the distribution from which observed knock intensities are drawn. Typically a simple threshold is applied, and the controller regulates the resultant knock event rate. Recent work suggests that the choice of threshold can have a significant impact on closed loop performance, but to date such studies have been performed only in simulation. Rigorous assessment of closed loop performance is also a challenging topic in its own right because response trajectories depend on the random arrival of knock events. The results therefore vary from one experiment to the next, even under identical operating conditions. To address this issue, stochastic simulation methods have been developed which aim to predict the expected statistics of the closed loop response, but again these have not been validated experimentally.

Vehicular control systems are characterized with numerous complex interactions with a steady rise of autonomous functions, which makes it more challenging for designers and safety engineers to identify unexpected failures. These systems tend to be highly integrated and exhibit features like concurrency for which traditional verification and validation techniques (i.e. testing and simulation) are insufficient to provide rigorous and complete assessment. Model Checking, a well-known formal verification technique, can be used to rigorously prove the correctness of such systems according to design Requirements. In particular, Model Checking is a method for formally verifying finite-state concurrent systems. Specifications about the system are expressed as temporal logic formulas, and efficient symbolic algorithms are used to traverse the model defined by the system and check if the specification holds or not.

The integration of sensors, actuators, and real-time control in transportation systems enables intelligent system operation to minimize energy consumption and maximize occupant safety and vehicle reliability. The operating cycle of military ground vehicles can be on- and off-road in harsh weather and adversarial environments, which demands continuous subsystem functionality to fulfill missions. Onboard diagnostic systems can alert the operator of a degraded operation once established fault thresholds are exceeded. An opportunity exists to estimate vehicle maintenance needs using model-based predicted trends and eventually compiled information from fleet operating databases. A digital twin, created to virtually describe the dynamic behavior of a physical system using computer-mathematical models, can estimate the system behavior based on current and future operating scenarios while accounting for past effects.

Range anxiety and lack of adequate access to fast charging are proving to be important impediments to electric vehicle (EV) adoption. While many techniques to fast charging EV batteries (model-based & model-free) have been developed, they have focused on a single Lithium-ion cell. Extensions to battery packs are scarce, often considering simplified architectures (e.g., series-connected) for ease of modeling. Computational considerations have also restricted fast-charging simulations to small battery packs, e.g., four cells (for both series and parallel connected cells). Hence, in this paper, we pursue a model-free approach based on reinforcement learning (RL) to fast charge a large battery pack (comprising 444 cells). Each cell is characterized by an equivalent circuit model coupled with a second-order lumped thermal model to simulate the battery behavior. After training the underlying RL, the developed model will be straightforward to implement with low computational complexity.