Filtering by
- All Subjects: engineering
- All Subjects: Machine Learning
Performance evaluation and characterization of lithium-ion cells under simulated PHEVs' drive cycles
In PHEVs, batteries operate under charge sustaining and charge depleting mode based on torque requirement and state of charge. In the current article, 26650 lithium-ion cells were cycled extensively at 25 and 50 oC under charge sustaining mode to monitor capacity and cell impedance values followed by analyzing the Lithium iron phosphate (LiFePO4) cathode material by X-ray diffraction analysis (XRD). High frequency resistance measured by electrochemical impedance spectroscopy was found to increase significantly under high temperature cycling, leading to power fading. No phase change in LiFePO4 cathode material is observed after 330 cycles at elevated temperature under charge sustaining mode from the XRD analysis. However, there was significant change in crystallite size of the cathode active material after charge/discharge cycling with charge sustaining mode. Additionally, 18650 lithium-ion cells were tested under charge depleting mode to monitor capacity values.
The objective of this research is to allocate tolerance values to ensure that the assemblability conditions are satisfied. Assemblability refers to “the ability to assemble/fit a set of parts in specified configuration given a nominal geometry and its corresponding tolerances”. Assemblability is determined by the clearances between the mating features. These clearances are affected by accumulation of tolerances in tolerance loops and hence, the tolerance loops are extracted first. Once tolerance loops have been identified initial tolerance values are allocated to the contributors in these loops. It is highly unlikely that the initial allocation would satisfice assemblability requirements. Overlapping loops have to be simultaneously satisfied progressively. Hence, tolerances will need to be re-allocated iteratively. This is done with the help of tolerance analysis module.
The tolerance allocation and analysis module receives the constraint graph which contains all basic dimensions and mating constraints from the generated schema. The tolerance loops are detected by traversing the constraint graph. The initial allocation distributes the tolerance budget computed from clearance available in the loop, among its contributors in proportion to the associated nominal dimensions. The analysis module subjects the loops to 3D parametric variation analysis and estimates the variation parameters for the clearances. The re-allocation module uses hill climbing heuristics derived from the distribution parameters to select a loop. Re-allocation Of the tolerance values is done using sensitivities and the weights associated with the contributors in the stack.
Several test cases have been run with this software and the desired user input acceptance rates are achieved. Three test cases are presented and output of each module is discussed.
The research presented in this Honors Thesis provides development in machine learning models which predict future states of a system with unknown dynamics, based on observations of the system. Two case studies are presented for (1) a non-conservative pendulum and (2) a differential game dictating a two-car uncontrolled intersection scenario. In the paper we investigate how learning architectures can be manipulated for problem specific geometry. The result of this research provides that these problem specific models are valuable for accurate learning and predicting the dynamics of physics systems.<br/><br/>In order to properly model the physics of a real pendulum, modifications were made to a prior architecture which was sufficient in modeling an ideal pendulum. The necessary modifications to the previous network [13] were problem specific and not transferrable to all other non-conservative physics scenarios. The modified architecture successfully models real pendulum dynamics. This case study provides a basis for future research in augmenting the symplectic gradient of a Hamiltonian energy function to provide a generalized, non-conservative physics model.<br/><br/>A problem specific architecture was also utilized to create an accurate model for the two-car intersection case. The Costate Network proved to be an improvement from the previously used Value Network [17]. Note that this comparison is applied lightly due to slight implementation differences. The development of the Costate Network provides a basis for using characteristics to decompose functions and create a simplified learning problem.<br/><br/>This paper is successful in creating new opportunities to develop physics models, in which the sample cases should be used as a guide for modeling other real and pseudo physics. Although the focused models in this paper are not generalizable, it is important to note that these cases provide direction for future research.
High-entropy alloys possessing mechanical, chemical, and electrical properties that far exceed those of conventional alloys have the potential to make a significant impact on many areas of engineering. Identifying element combinations and configurations to form these alloys, however, is a difficult, time-consuming, computationally intensive task. Machine learning has revolutionized many different fields due to its ability to generalize well to different problems and produce computationally efficient, accurate predictions regarding the system of interest. In this thesis, we demonstrate the effectiveness of machine learning models applied to toy cases representative of simplified physics that are relevant to high-entropy alloy simulation. We show these models are effective at learning nonlinear dynamics for single and multi-particle cases and that more work is needed to accurately represent complex cases in which the system dynamics are chaotic. This thesis serves as a demonstration of the potential benefits of machine learning applied to high-entropy alloy simulations to generate fast, accurate predictions of nonlinear dynamics.
The robustness of a neural network is defined as the stability of the network output under small input perturbations. It has been shown that neural networks are very sensitive to input perturbations, and the prediction from convolutional neural networks can be totally different for input images that are visually indistinguishable to human eyes. Based on such property, hackers can reversely engineer the input to trick machine learning systems in targeted ways. These adversarial attacks have shown to be surprisingly effective, which has raised serious concerns over safety-critical applications like autonomous driving. In the meantime, many established defense mechanisms have shown to be vulnerable under more advanced attacks proposed later, and how to improve the robustness of neural networks is still an open question.
The generalizability of neural networks refers to the ability of networks to perform well on unseen data rather than just the data that they were trained on. Neural networks often fail to carry out reliable generalizations when the testing data is of different distribution compared with the training one, which will make autonomous driving systems risky under new environment. The generalizability of neural networks can also be limited whenever there is a scarcity of training data, while it can be expensive to acquire large datasets either experimentally or numerically for engineering applications, such as material and chemical design.
In this dissertation, we are thus motivated to improve the robustness and generalizability of neural networks. Firstly, unlike traditional bottom-up classifiers, we use a pre-trained generative model to perform top-down reasoning and infer the label information. The proposed generative classifier has shown to be promising in handling input distribution shifts. Secondly, we focus on improving the network robustness and propose an extension to adversarial training by considering the transformation invariance. Proposed method improves the robustness over state-of-the-art methods by 2.5% on MNIST and 3.7% on CIFAR-10. Thirdly, we focus on designing networks that generalize well at predicting physics response. Our physics prior knowledge is used to guide the designing of the network architecture, which enables efficient learning and inference. Proposed network is able to generalize well even when it is trained with a single image pair.