Search Results

Identifying edge cases for designed algorithms is critical for functional safety in autonomous driving deployment. In order to find the feasible boundary of designed algorithms, simulations are heavily used. However, simulations for autonomous driving validation are expensive due to the requirement of visual rendering, physical simulation, and AI agents. In this case, common sampling techniques, such as Monte Carlo Sampling, become computationally expensive due to their sample inefficiency. To improve sample efficiency and minimize the number of simulations, we propose a tailored active learning approach combining the Support Vector Machine (SVM) and the Gaussian Process Regressor (GPR). The SVM learns the feasible boundary iteratively with a new sampling point via active learning. Active Learning is achieved by using the information of the decision boundary of the current SVM and the uncertainty metric calculated by the GPR.

Light weight structures give significant advantages to products in the Industrial sector. Component weight-saving plays a major role in improving the efficiency and performance of assembled systems. The introduction of lighter materials into products using dissimilar material joining techniques can create more weight savings and leads to lighter structures. Structural optimization is another method to optimize the material layout without affecting overall performance of the product. This paper discusses the methods to create lighter structures by the introduction of lighter materials in structures and structural optimization methods. Lighter materials are introduced in the structure using dissimilar material joining techniques. Joining processes such as thermal shrink-fit and mechanical press-fit are useful for metal to metal components. Similarly, adhesively bonded joints are useful for both metal and non-metal (plastics and composites) components.

The effects of downspeeding and supercharging a passenger car diesel engine were studied through laboratory investigation and vehicle simulation. Changes in the engine operating range, transmission gearing, and shift schedule resulted in improved fuel consumption relative to the baseline turbocharged vehicle while maintaining performance and drivability metrics. A shift schedule optimization technique resulted in fuel economy gains of up to 12% along with a corresponding reduction in transmission shift frequency of up to 55% relative to the baseline turbocharged configuration. First gear acceleration, top gear passing, and 0-60 mph acceleration of the baseline turbocharged vehicle were retained for the downsped supercharged configuration.

A simulation framework with a validated system model capable of estimating fuel consumption is a valuable tool in analysis and design of the hybrid vehicles. In particular, the framework can be used for (1) benchmarking the fuel economy achievable from alternate hybrid powertrain technologies, (2) investigating sensitivity of fuel savings with respect to design parameters (for example, component sizing), and (3) evaluating the performance of various supervisory control algorithms for energy management. This paper describes such a simulation framework that can be used to predict fuel economy of series hydraulic hybrid vehicle for any specified driver demand schedule (drive cycle), developed in MATLAB/Simulink. The key components of the series hydraulic hybrid vehicle are modeled using a combination of first principles and empirical data. A simplified driver model is included to follow the specified drive cycle.

The Mississippi State University Formula SAE race car upright was optimized using radial basis function metamodels and an internal state variable (ISV) plasticity damage material model. The weight reduction of the upright was part of a goal to reduce the weight of the vehicle by 25 percent. Using an optimization routine provided an upright design that is lighter that helps to improve vehicle fuel economy, acceleration, and handling. Finite element (FE) models of the upright were produced using quadratic tetrahedral elements. Using tetrahedral elements provided a quick way to produce the multiple FE models of the upright required for the multi-objective optimization. A design of experiments was used to determine how many simulations were required for the optimization. The loads for the simulations included braking, acceleration, and corning loads seen by the car under track conditions.

Optimal fuel injection strategies are obtained with a micro-genetic algorithm and an adaptive gradient method for a nonroad, medium-speed DI diesel engine equipped with a multi-orifice, asynchronous fuel injection system. The gradient optimization utilizes a fast-converging backtracking algorithm and an adaptive cost function which is based on the penalty method, where the penalty coefficient is increased after every line search. The micro-genetic algorithm uses parameter combinations of the best two individuals in each generation until a local convergence is achieved, and then generates a random population to continue the global search. The optimizations have been performed for a two pulse fuel injection strategy where the optimization parameters are the injection timings and the nozzle orifice diameters.

A previously developed CFD-based optimization tool is utilized to find optimal engine operating conditions with respect to fuel consumption and emissions. The optimization algorithm employed is based on the steepest descent method where an adaptive cost function is minimized along each line search using an effective backtracking strategy. The adaptive cost function is based on the penalty method, where the penalty coefficient is increased after every line search. The parameter space is normalized and, thus, the optimization occurs over the unit cube in higher-dimensional space. The application of this optimization tool is demonstrated for the Sulzer S20, a central-injection, non-road DI diesel engine. The optimization parameters are the start of injection of the two pulses of a split injection system, the duration of each pulse, the exhaust gas recirculation rate, the boost pressure and the compression ratio.

A global optimization method has been developed for an engine simulation code and utilized in the search of optimal fuel injection strategies. This method uses a Lagrange interpolation function which interpolates engine output data generated at the vertices and the intermediate points of the input parameters. This interpolation function is then used to find a global minimum over the entire parameter set, which in turn becomes the starting point of a CFD-based optimization. The CFD optimization is based on a steepest descent method with an adaptive cost function, where the line searches are performed with a fast-converging backtracking algorithm. The adaptive cost function is based on the penalty method, where the penalty coefficient is increased after every line search. The parameter space is normalized and, thus, the optimization occurs over the unit cube in higher-dimensional space.

Extensive experimental and numerical investigations were done to improve the vibration and acoustic performance due to excitation at the timing gears of automotive supercharger. Gear excitation, system response, and covers have been studied to find the most cost efficient method for reducing gear whine noise. Initially, gear excitation was studied where it was found that transmission error due to profile quality was the dominant source parameter for gear whine noise. To investigate the system effects on gear noise, a parametric study was carried using FEM model of the supercharger, with special interests in optimizing dynamic characteristics of internal components and the coupling to supercharger housing. The BEM model of the corresponding supercharger was built to predict the noise improvement after dynamic optimization of the system. Good correlations were observed between experimental and numerical results in both dynamic and acoustic parameters.

A numerical simulation and optimization study was conducted for a medium speed direct injection diesel engine. The engine's operating characteristics were first matched to available experimental data to test the validity of the numerical model. The KIVA-3V ERC CFD code was then modified to allow independent spray events from two rows of nozzle holes. The angular alignment, nozzle hole size, and injection pressure of each set of nozzle holes were optimized using a micro-genetic algorithm. The design fitness criteria were based on a multi-variable merit function with inputs of emissions of soot, NOx, unburned hydrocarbons, and fuel consumption targets. Penalties to the merit function value were used to limit the maximum in-cylinder pressure and the burned gas temperature at exhaust valve opening. The optimization produced a 28.4% decrease in NOx and a 40% decrease in soot from the baseline case, while giving a 3.1% improvement in fuel economy.

The power management control system development and vehicle test results for a medium-duty hybrid electric truck are reported in this paper. The design procedure adopted is a model-based approach, and is based on the dynamic programming technique. A vehicle model is first developed, and the optimal control actions to maximize fuel economy are then obtained by the dynamic programming method. A near-optimal control strategy is subsequently extracted and implemented using a rapid-prototyping control development system, which provides a convenient environment to adjust the control algorithms and accommodate various I/O configurations. Dynamometer-testing results confirm that the proposed algorithm helps the prototype hybrid truck to achieve a 45% fuel economy improvement on the benchmark (non-hybrid) vehicle. It also compares favorably to a conventional rule-based control method, which only achieves a 31% fuel economy improvement on the same hybrid vehicle.

Neural networks are useful tools for optimization studies since they are very fast, so that while capturing the accuracy of multi-dimensional CFD calculations or experimental data, they can be run numerous times as required by many optimization techniques. This paper describes how a set of neural networks trained on a multi-dimensional CFD code to predict pressure, temperature, heat flux, torque and emissions, have been used by a genetic algorithm in combination with a hill-climbing type algorithm to optimize operating parameters of a diesel engine over the entire speed-torque map of the engine. The optimized parameters are mass of fuel injected per cycle, shape of the injection profile for dual split injection, start of injection, EGR level and boost pressure. These have been optimized for minimum emissions. Another set of neural networks have been trained to predict the optimized parameters, based on the speed-torque point of the engine.

A study of the combined use of split injections, EGR, and flexible boosting was conducted. Statistical optimization of the engine operating parameters was accomplished using a new response surface method. The objective of the study was to demonstrate the emissions and fuel consumption capabilities of a state-of-the-art heavy -duty diesel engine when using split injections, EGR, and flexible boosting over a wide range of engine operating conditions. Previous studies have indicated that multiple injections with EGR can provide substantial simultaneous reductions in emissions of particulate and NOx from heavy-duty diesel engines, but careful optimization of the operating parameters is necessary in order to receive the full benefit of these combustion control techniques. Similarly, boost has been shown to be an important parameter to optimize. During the experiments, an instrumented single-cylinder heavy -duty diesel engine was used.

A study of statistical optimization of engine operating parameters was conducted. The objective of the study was to develop a strategy to efficiently optimize operating parameters of diesel engines with multiple injection and EGR capabilities. Previous studies have indicated that multiple injections with EGR can provide substantial simultaneous reductions in emissions of particulate and NOx from heavy-duty diesel engines, but careful optimization of the operating parameters is necessary in order to receive the full benefit of these combustion control techniques. The goal of the present study was to optimize the control parameters to reduce emissions and brake specific fuel consumption. An instrumented single-cylinder heavy-duty diesel engine was used with a prototype mechanically actuated (cam driven) fuel injection system.

This Paper introduces a modular, flexible and user-friendly dynamic powertrain model of the US Army's High Mobility Multi-Wheeled Vehicle (HMMWV). It includes the DDC 6.5L diesel engine, Hydra-matic 4L80-E automatic transmission, Torsen differentials, transfer case, and flexible drive and axle shafts. This model is used in a case study on transmission optimization design to demonstrate an application of the model. This study shows how combined optimization of the transmission hardware (clutch capacity) and control strategy (shift time) can be explored, and how the models can help the designer understand dynamic interactions as well as provide useful design guidance early in the system design phase.