<p>EfficientNet is designed to achieve top accuracy while utilizing fewer parameters, in addition to less computational resources compared to previous models. </p> <p><br></p> <p>In this paper, we are presenting compound scaling method that re-weight the network's width (w), depth (d), and resolution (r), which leads to better performance than traditional methods that scale only one or two of these dimensions by adjusting the hyperparameters of the model. Additionally, we are presenting an enhanced EfficientNet Backbone architecture. </p> <p><br></p> <p>We show that EfficientNet achieves top accuracy on the ImageNet dataset, while being up to 8.4x smaller and up to 6.1x faster than previous top performing models. The effectiveness demonstrated in EfficientNet on transfer learning and object detection tasks, where it achieves higher accuracy with fewer parameters and less computation. Henceforward, the proposed enhanced architecture will be discussed in detail and compared to the original architecture.</p> <p><br></p> <p>Our approach provides a scalable and efficient solution for both academic research and practical applications, where resource constraints are often a limiting factor.</p> <p><br></p>

<div>Pressure compensated vane pump systems are an attractive solution in many automotive applications to supply hydraulic power required for cooling, lubrication, and actuation of control elements such as transmission clutches. These systems feature variable displacement vane pumps which offer reductions in parasitic loads on the engine and in wasted hydraulic energy at high engine speeds when compared to traditional fixed displacement supply pumps. However, oscillations in a currently available pressure compensation system limits the achievable performance and therefore the application of this solution.</div><div>This dissertation presents the development and experimental validation of a lumped parameter model in MATLAB/Simulink of a current pressure compensated vane pump system for an automatic transmission oil supply application. An analysis of the performance of this system using the validated pump model and a developed black box control system model reveals that the low cost solenoid valve present in the control circuit to set the regulation pressure limits the achievable bandwidth to 1.84Hz and causes a significant time delay in the response. To address this limitation, as well as eliminate a non-minimum phase zero introduced by the case study’s control circuit architecture, an actively controlled electrohydraulic pressure compensation system is proposed. This proposed system is explored both experimentally and in simulation making use of the accuracy of the presented variable displacement vane pump model. Significant improvements in the achievable system performance are shown with both a simple PI control law (47% reduction in the pressure response time) and an advanced cascaded model following controller based on feedback linearization (58% reduction in the pressure response time). An analysis of these results reveals that implementing the proposed control system with a 5(L/min)/bar proportional valve with a 20Hz at ±100% (60Hz at ±50%) amplitude bandwidth and a PI control law is an economical path to achieving the best performance improvements for this automotive application.</div>

<div>Efficient engine operation is a fundamental control problem in automotive applications. Robust control algorithms are necessary to achieve satisfactory, safe engine performance</div><div>at all operating conditions while reducing emissions. This thesis develops a framework for control architecture design to enable robust air handling system management.</div><div><br></div><div>The first work in the thesis derives a simple physics-based, control-oriented model for turbocharged lean burn engines which is able to capture the critical engine dynamics that are</div><div>needed to design the controller. The control-oriented model is amenable for control algorithm development and includes the impacts of modulation to any combination of four actuators: throttle valve, bypass valve, fuel rate, and wastegate valve. The controlled outputs: engine speed, differential pressure across throttle and air-to-fuel ratio are modeled as functions of selected states and inputs. Two validation strategies, open-loop and closed-loop are used to validate the accuracy of both nonlinear and linear versions of the control-oriented model. The relative gain array is applied to the linearized engine model to understand the degree of interactions between plant inputs and outputs as well as the best input-output pairing as a function of frequency. With strong evidence of high degree of coupling between inputs and outputs, a coordinated multiple-input multiple-output (MIMO) controller is hypothesized to perform better than a single-input single-output (SISO) controller. A framework to design robust model-based H1 MIMO controllers for any given linear plant, while considering state and output multiplicative uncertainties as well as actuator bandwidths is developed. The framework also computes the singular structure value, μ for the uncertain closed-loop system to quantify robustness, both in terms of stability and performance. The multi-tracking control problem targets engine speed, differential pressure across throttle as well as air-to-fuel ratio to achieve satisfactory engine performance while also preventing compressor surge and reducing engine emissions. A controller switching methodology using slow-fast controller decomposition and hysteresis at switching points is proposed to smoothly switch control authority between several MIMO controllers. The control design approach is applied to a truth-reference GT-Power engine model to evaluate the closed-loop controller performance. The engine response obtained using the robust MIMO controller is compared with that obtained using a state-of-the-art benchmark controller to evaluate the additional benefits of the MIMO controller.</div><div><br></div><div><div>In the second study, a robust 2-degree of freedom controller that commands eBooster speed to control air-to-fuel ratio, and a robust MIMO coordinated controller to control gas</div><div>exchange process in a diesel engine with electrified air handling architecture are developed. The MIMO controller simultaneously controls engine speed, mass fraction of the recirculated exhaust gas as well as air-to-fuel ratio. The actuators available for control in the engine include the exhaust gas recirculation valve, exhaust throttle valve, fuel injection rate, eBooster speed, eBooster bypass valve. To design the robust eBooster controller, the input-output relationship between eBooster speed and air-to-fuel ratio is estimated using system identification techniques. The robust MIMO controller is synthesized using a physics-based mean value control-oriented engine model that accurately represents the high-fidelity GT-Power model. In the first control strategy, the robust eBooster controller is added to an already existing stock engine control unit while in the second control strategy, the stock engine control unit is replaced with the multiple-input multiple-output controller. The two control architectures are tested under different operating conditions to evaluate the controller performance. Simulation results with the control architectures developed in the thesis are compared to a baseline engine configuration, where the engine operates without eBooster. Although it is observed that both these control algorithms significantly improve engine performance as compared to the baseline configuration, MIMO controller provides the best engine performance overall.</div></div>

Increase in the awareness environmental conservation is leading the automotive industry into the adaptation of alternatively fueled vehicles. Electric, Fuel-Cell as well as Hybrid-Electric vehicles focus on this research area with aim to efficiently utilize vehicle powertrain as the first step. Energy and Power Management System control strategies play vital role in improving efficiency of any hybrid propulsion system. However, these control strategies are sensitive to the dynamics of the powertrain components used in the given system. A kinematic mathematical model for Plug-in Hybrid Electric Vehicle (PHEV) has been developed in this study and is further optimized by determining optimal power management strategy for minimal fuel consumption as well as NOx emissions while executing a set drive cycle. A multi-objective optimization using weighted sum formulation is needed in order to observe the trade-off between the optimized objectives. Particle Swarm Optimization (PSO) algorithm has been used in this research, to determine the trade-off curve between fuel and NOx. In performing these optimizations, the control signal consisting of engine speed and reference battery SOC trajectory for a 2-hour cycle is used as the controllable decision parameter input directly from the optimizer. Each element of the control signal was split into 50 distinct points representing the full 2 hours, giving slightly less than 2.5 minutes per point, noting that the values used in the model are interpolated between the points for each time step. With the control signal consisting of 2 distinct signals, speed and SOC trajectory, as 50 element time variant signals, a multidimensional problem was formulated for the optimizer. Novel approaches to balance the optimizer exploration and convergence, as well as seeding techniques are suggested to solve the optimal control problem. The optimization of each involved individual runs at 5 different weight levels with the resulting cost populations being compiled together to visually represent with the help of Pareto front development. The obtained results of simulations and optimization are presented involving performances of individual components of the PHEV powertrain as well as the optimized PMS strategy to follow for given drive cycle. Observations of the trade-off is discussed in the case of Multi-Objective Optimizations.

Les matériaux composites sont largement utilisés dans l'industrie automobile comme pièces de structure. Alliant légèreté et bonnes propriétés mécaniques, ils ont remplacé les métaux classiquement adoptés dans la fabrication de moyens de transport. Toutefois, l'emploi des matériaux composites doit tenir compte de leur comportement électromagnétique. En effet, les composites à fibres conductrices, généralement moins conducteurs que les métaux, engendrent une interaction avec les ondes électromagnétiques, différente de celle introduite par les alliages métalliques. Il s'avère donc important de développer des outils de modélisation permettant de mieux appréhender le comportement électromagnétique de matériaux composites, et d'éclairer les changements qu'apportent ces matériaux sur la distribution des champs, provenant d'une multitude de sources externes, au voisinage des systèmes mécatroniques. Par ailleurs, l'étude du comportement électromagnétique de matériaux composites permet de tirer parti de leurs propriétés mécaniques attractives afin d'alléger les boîtiers de blindage en gardant un niveau d'atténuation conforme aux normes de l'industrie. Cependant, la modélisation numérique de structures composites de grande taille, telles que les boîtiers de blindage, bien que classiquement adoptée pour les structures métalliques, est rendue complexe par le fait que les composites présentent des hétérogénéités à l'échelle microscopique, et que leurs mécanismes de blindage diffèrent de ceux des conducteurs homogènes. Le calcul numérique s'avère envisageable une fois le composite remplacé par un matériau homogène ayant une réponse identique face à une sollicitation électromagnétique. Ainsi, au travers de ce travail de thèse, nous proposons une technique d'homogénéisation permettant d'estimer les propriétés électriques équivalentes que nous appliquons aux composites à fibres conductrices unidirectionnelles et tissées. Les résultats obtenus sont utilisés pour la simulation numérique d'un boîtier de blindage. / Composite materials are widely used in the automotive industry as structural components. By combining lightness and robust mechanical properties, they are increasigly replacing the conventionnally used metallic alloys, for the manufacturing of vehicle parts. However, the use of composite materials is not without consequences on the electromagnetic behavior of these parts. Since carbon fiber reinforced composites are generally worse conductors of electricity than metals, they interact differently with the electromagnetic waves which surround them. It is therefore important to develop modeling tools to better understand the electromagnetic behavior of composite materials. This is to explain the changes that these materials bring to the distribution of waves, generated by a multitude of external sources, in the vicinity of mechatronic systems. On the other hand, the study of the electromagnetic behavior of composite materials makes it possible to determine the possibility of taking advantage of their attractive mechanical properties in order to further reduce the weight of electromagnetic shielding enclosures while maintaining a level of attenuation in accordance with the standards of the industry. However, numerical modeling of large composite structures, such as shielding enclosures, although conventionally adopted for metal structures, is hindered by the fact that composites exhibit heterogeneities at the microscopic scale. The numerical calculation becomes possible once the composite is replaced by a homogeneous material that exhibits an identical response to an identical electromagnetic solicitation. In this work, we present a homogenization technique, based on finite element simulation and an optimisation method, that computes an estimate of the equivalent electrical properties of unidirectional and woven fiber reinforced composites. The results are then used to simulate the shielding effectiveness of an enclosure constructed by combining composite materials and metallic alloys.

<div>Polymer nanocomposites (PNC) have an excellent potential for in-situ strain sensing applications in static and dynamic loading scenarios. These PNCs have a polymer matrix of polyvinylidene fluoride (PVDF) with a conductive filler of multi-walled carbon nanotubes (MWCNT) and have both piezoelectric and piezoresistive characteristics. Generally, this composite would accurately measure either low-frequency dynamic strain using piezoresistive characteristic or high-frequency dynamic strains using piezoelectric characteristics of the MWCNT/PVDF film sensor. Thus, the frequency bands of the strain sensor are limited to either piezoresistive or piezoelectric ranges. In this study, a novel weighted fusion technique, called Piezoresistive/Piezoelectric Fusion (PPF), is proposed to combine both piezoresistive and piezoelectric characteristics to capture the wide frequency bands of strain measurements in real-time. This fuzzy logic (FL)-based method combines the salient features (i.e., piezoresistive and piezoelectric) of the nanocomposite sensor via reasonably accurate models to extend the frequency range over a wider band. The FL determines the weight of each signal based on the error between the estimated measurements and the actual measurements. These weights indicate the contribution of each signal to the final fused measurement. The Fuzzy Inference System (FIS) was developed using both optimization and data clustering techniques. In addition, a type-2 FIS was utilized to overcome the model’s uncertainty limitations. The developed PPF methods were verified with experimental data at different dynamic frequencies that were obtained from existing literature. The fused measurements of the MWCNT/PVDF were found to correlate very well with the actual strain, and a high degree of accuracy was achieved by the subtractive clustering PPF’s FISs algorithm. <br></div><div><br></div><div>3D force sensors have proven their effectiveness and relevance for robotics applications. They have also been used in medical and physical therapy applications such as surgical robots and Instrument Assisted Soft Tissue Manipulation (IASTM). The 3D force sensors have been utilized in robot-assisted surgeries and modern physical therapy devices to monitor the 3D forces for improved performances. The 3D force sensor performance and specifications depend on different design parameters, such as the structural configuration, placement of the sensing elements, and load criterion. In this work, different bioinspired structure configurations have been investigated and analyzed to obtain the optimal 3D force sensor configuration in terms of structural integrity, compactness, the safety factor, and strain sensitivity. A Finite Element Analysis (FEA) simulation was used for the analysis to minimize the time of the development cycle.</div><div><br></div><div><br></div><div>A tree branch design was used as the 3D force sensor’s elastic structure. The structure was made of aluminum with a laser-cutting fabrication process. The PVDF/MWCNT films contained piezoresistive and piezoelectric characteristics that allowed for static/low strain measurements and dynamic strain measurements, respectively. Two compositions with 0.1 wt.% and 2 wt.% PVDF/MWCNT sensing elements were selected for piezoelectric and piezoresistive strain measurements, respectively. These characteristic measurements were investigated under different vibration rates in a supported beam experiment. The 3D force sensor was tested under dynamic excitation in the Z-direction and the X-direction. A Direct Piezoresistive/Piezoelectric Fusion (DPPF) method was developed by fusing the piezoresistive and piezoelectric measurements at a given frequency that overcomes the limited frequency ranges of each of the strain sensor characteristics. The DPPF method is based on a fuzzy inference system (FIS) which is constructed and tuned using the subtractive clustering technique. Different nonlinear Hammerstein-Wiener (nlhw) models were used to estimate the actual strain from piezoresistive and piezoelectric measurements at the 3D force sensor. The DPPF method was tested and validated for different strain signal types using presumed Triangle and Square signal waves data. The DPPF has proven its effectiveness in fusing piezoresistive and piezoelectric measurements with different types of signals. In addition, an Extended Direct Piezoresistive/Piezoelectric Fusion (EPPF) is introduced to enhance the DPPF method and perform the fusion in a range of frequencies instead of a particular one. The DPPF and EPPF methods were implemented on the 3D force sensor data, and the developed fusion algorithms were tested on the proposed 3D force sensor experimental data. The simulation results show that the proposed fusion methods have been effective in achieving lower Root Mean Square Error (RMSE) than those obtained from the tuned nlhw models at different operating frequencies.</div>

<p>Stringent regulatory requirements and modern diesel engine technologies have engaged automotive manufacturers and researchers in accurately predicting and controlling diesel engine-out emissions. As a result, engine control systems have become more complex and opaquer, increasing the development time and costs. To address this challenge, Model-based control methods are an effective way to deal with the criticality of the system study and controls. And physics-based combustion engine modeling is a key to achieve it. This thesis focuses on development and validation of a physics-based model for both engine and emissions using model-based design tools from MATLAB & Simulink. Engine model equipped with exhaust gas circulation and variable geometry turbine is adopted from the previously done work which was then integrated with the combustion and emission model that predicts the heat release rates and NO_xemission from engine. Combustion model is designed based on the mass fraction burnt from CA10 to CA90 and then NO_xpredicted using the extended Zeldovich mechanism. The engine models are tuned for both steady state and dynamics test points to account for engine operating range from the performance data. Various engine and combustion parameters are estimated using parameter estimation toolbox from MATLAB and Simulink by applying least squared solver to minimize the error between measured and estimated variables. This model is validated against the virtual engine model developed in GT-power for Cummins 6.7L turbo diesel engine. To account the harmonization of the testing cycles to save engine development time globally, a world harmonized stationary cycle (WHSC) is used for the validation. Sub-systems are validated individually as well as in loop with a complete model for WHSC. Engine model validation showed promising accuracy of more than 88.4 percent in average for the desired parameters required for the NO_xprediction. NO_x estimation is accurate for the cycle except warm up and cool down phase. However, NO_xprediction during these phases is limited due to actual NO_xmeasured data for tuning the model for real time NO_xestimation. Results are summarized at the end to compare the trend of NO_xestimation from the developed combustion and emission model to show the accuracy of in-cylinder parameters and required for the NO_x estimation. </p>

<div>Stoichiometric air-fuel ratio (AFR) and air/EGR flow control are essential control problems in today’s advanced spark-ignited (SI) engines to enable effective application of the three-way-catalyst (TWC) and generation of required torque. External exhaust gas recirculation (EGR) can be used in SI engines to help mitigate knock, reduce enrichment and improve efficiency[1 ]. However, the introduction of the EGR system increases the complexity of stoichiometric engine-out lambda and torque management, particularly for high BMEP commercial vehicle applications. This thesis develops advanced frameworks for sensing and control architecture designs to enable robust air handling system management, stoichiometric cylinder air-fuel ratio (AFR) control and three-way-catalyst emission control.</div><div><br></div><div><div>The first work in this thesis derives a physically-based, control-oriented model for turbocharged SI engines utilizing cooled EGR and flexible VVA systems. The model includes the impacts of modulation to any combination of 11 actuators, including the throttle valve, bypass valve, fuel injection rate, waste-gate, high-pressure (HP) EGR, low-pressure (LP) EGR, number of firing cylinders, intake and exhaust valve opening and closing timings. A new cylinder-out gas composition estimation method, based on the inputs’ information of cylinder charge flow, injected fuel amount, residual gas mass and intake gas compositions, is proposed in this model. This method can be implemented in the control-oriented model as a critical input for estimating the exhaust manifold gas compositions. A new flow-based turbine-out pressure modeling strategy is also proposed in this thesis as a necessary input to estimate the LP EGR flow rate. Incorporated with these two sub-models, the control-oriented model is capable to capture the dynamics of pressure, temperature and gas compositions in manifolds and the cylinder. Thirteen physical parameters, including intake, boost and exhaust manifolds’ pressures, temperatures, unburnt and burnt mass fractions as well as the turbocharger speed, are defined as state variables. The outputs such as flow rates and AFR are modeled as functions of selected states and inputs. The control-oriented model is validated with a high fidelity SI engine GT-Power model for different operating conditions. The novelty in this physical modeling work includes the development and incorporation of the cylinder-out gas composition estimation method and the turbine-out pressure model in the control-oriented model.</div></div><div><br></div><div><div>The second part of the work outlines a novel sensor selection and observer design algorithm for linear time-invariant systems with both process and measurement noise based on <i>H</i>2 optimization to optimize the tradeoff between the observer error and the number of required sensors. The optimization problem is relaxed to a sequence of convex optimization problems that minimize the cost function consisting of the <i>H</i>2 norm of the observer error and the weighted <i>l</i>1 norm of the observer gain. An LMI formulation allows for efficient solution via semi-definite programing. The approach is applied here, for the first time, to a turbo-charged spark-ignited (SI) engine using exhaust gas recirculation to determine the optimal sensor sets for real-time intake manifold burnt gas mass fraction estimation. Simulation with the candidate estimator embedded in a high fidelity engine GT-Power model demonstrates that the optimal sensor sets selected using this algorithm have the best <i>H</i>2 estimation performance. Sensor redundancy is also analyzed based on the algorithm results. This algorithm is applicable for any type of modern internal combustion engines to reduce system design time and experimental efforts typically required for selecting optimal sensor sets.</div></div><div><br></div><div><div>The third study develops a model-based sensor selection and controller design framework for robust control of air-fuel-ratio (AFR), air flow and EGR flow for turbocharged stoichiometric engines using low pressure EGR, waste-gate turbo-charging, intake throttling and variable valve timing. Model uncertainties, disturbances, transport delays, sensor and actuator characteristics are considered in this framework. Based on the required control performance and candidate sensor sets, the framework synthesizes an H1 feedback controller and evaluates the viability of the candidate sensor set through analysis of the structured</div><div>singular value μ of the closed-loop system in the frequency domain. The framework can also be used to understand if relaxing the controller performance requirements enables the use of a simpler (less costly) sensor set. The sensor selection and controller co-design approach is applied here, for the first time, to turbo-charged engines using exhaust gas circulation. High fidelity GT-Power simulations are used to validate the approach. The novelty of the work in this part can be summarized as follows: (1) A novel control strategy is proposed for the stoichiometric SI engines using low pressure EGR to simultaneously satisfy both the AFR and air/EGR-path control performance requirements; (2) A parametrical method to simultaneously select the sensors and design the controller is first proposed for the internal combustion engines.</div></div><div><br></div><div><div>In the fourth part of the work, a novel two-loop estimation and control strategy is proposed to reduce the emission of the three-way-catalyst (TWC). In the outer loop, an FOS estimator consisting of a TWC model and an extended Kalman-filter is used to estimate the current TWC fractional oxygen state (FOS) and a robust controller is used to control the TWC FOS by manipulating the desired engine λ. The outer loop estimator and controller are combined with an existing inner loop controller. The inner loop controller controls the engine λ based on the desired λ value and the control inaccuracies are considered and compensated by the outer loop robust controller. This control strategy achieves good emission reduction performance and has advantages over the constant λ control strategy and the conventional two-loop switch-type control strategy.</div></div>

<p>The miniaturization and thinning of wearable, soft robotics and medical devices are soon to require higher performance modeling as the physical flexibility causes direct impacts on the electrical characteristics of the circuit – changing its behavior. As a representative flexible electronic component, the organic field effect transistor (OFET) has attracted much attention in its manufacturing as well as applications. However, as the strain and stress effects are integrated into multiphysics modelers with deeper interactions, the computational complexity and accuracy of OFET modeling is resurfacing as a limiting bottleneck.</p><p>The dissertation was organized into three interrelated studies. In the first study, the Mass-Spring-Damper (MSD) model for an inverted staggered thin film transistor (TFT) was proposed to investigate the TFT’s internal stress/strain fields, and the strain effects on the overall characteristics of the TFT. A comparison study with the finite element analysis (FEA) model shows that the MSD model can reduce memory usage and raises the computational convergence speed for rendering the same results as the FEA. The second study developed the generalized solid-state model by incorporating the density of trap states in the band structure of organic semiconductors (OSCs). The introduction of trap states allows the generalized solid-state model to describe the electrical characteristics of both inorganic TFTs and organic field-effect transistors (OFETs). It is revealed through experimental verification that the generalized solid-state model can accurately characterize the bending induced electrical properties of an OFET in the linear and saturation regimes. The third study aims to model the transient and steady-state dynamics of an arbitrary organic semiconductor device under mechanical strain. In this study, the fractional drift-diffusion (Fr-DD) model and its computational scheme with high accuracy and high convergence rate were proposed. Based on simulation and experimental validation, the transconductance and output characteristics of a bendable OFET were found to be well determined by the Fr-DD model not only in the linear and saturation regimes, but also in the subthreshold regime.</p>