Filtering by
- All Subjects: Industrial Engineering
- Creators: Mirchandani, Pitu
- Status: Published
Two general approaches are developed. Both approximate the effects of recourse decisions without actually solving a stochastic model. The first approach procures more reserve whenever approximate recourse policies stress the transmission network. The second approach procures reserve at prime locations by generalizing the existing practice of reserve disqualification. The latter approach is applied for feasibility and is later extended to limit scenario costs. Testing demonstrates expected cost improvements around 0.5%-1.0% for the IEEE 73-bus test case, which can translate to millions of dollars per year even for modest systems. The heuristics developed in this dissertation perform somewhere between established deterministic and stochastic models: providing an economic benefit over current practices without substantially increasing computational times.
In this paper, a literature review is presented on the application of Bayesian networks applied in system reliability analysis. It is shown that Bayesian networks have become a popular modeling framework for system reliability analysis due to the benefits that Bayesian networks have the capability and flexibility to model complex systems, update the probability according to evidences and give a straightforward and compact graphical representation. Research on approaches for Bayesian network learning and inference are summarized. Two groups of models with multistate nodes were developed for scenarios from constant to continuous time to apply and contrast Bayesian networks with classical fault tree method. The expanded model discretized the continuous variables and provided failure related probability distribution over time.
Ultimate Frisbee or "Ultimate," is a fast growing field sport that is being played competitively at universities across the country. Many mid-tier college teams have the goal of winning as many games as possible, however they also need to grow their program by training and retaining new players. The purpose of this project was to create a prototype statistical tool that maximizes a player line-up's probability of scoring the next point, while having as equal playing time across all experienced and novice players as possible. Game, player, and team data was collected for 25 different games played over the course of 4 tournaments during Fall 2017 and early Spring 2018 using the UltiAnalytics iPad application. "Amount of Top 1/3 Players" was the measure of equal playing time, and "Line Efficiency" and "Line Interaction" represented a line's probability of scoring. After running a logistic regression, Line Efficiency was found to be the more accurate predictor of scoring outcome than Line Interaction. An "Equal PT Measure vs. Line Efficiency" graph was then created and the plot showed what the optimal lines were depending on what the user's preferences were at that point in time. Possible next steps include testing the model and refining it as needed.
The first step in process improvement is to scope the problem, next is measure the current process, but if data is not readily available and cannot be manually collected, then a measurement system must be implemented. General Dynamics Mission Systems (GDMS) is a lean company that is always seeking to improve. One of their current bottlenecks is the incoming inspection department. This department is responsible for finding defects on parts purchased and is critical to the high reliability product produced by GDMS. To stay competitive and hold their market share, a decision was made to optimize incoming inspection. This proved difficult because no data is being collected. Early steps in many process improvement methodologies, such as Define, Measure, Analyze, Improve and Control (DMAIC), include data collection; however, no measurement system was in place, resulting in no available data for improvement. The solution to this problem was to design and implement a Management Information System (MIS) that will track a variety of data. This will provide the company with data that will be used for analysis and improvement. The first stage of the MIS was developed in Microsoft Excel with Visual Basic for Applications because of the low cost and overall effectiveness of the software. Excel allows update to be made quickly, and allows GDMS to collect data immediately. Stage two would be moving the MIS to a more practicable software, such as Access or MySQL. This thesis is only focuses on stage one of the MIS, and GDMS will proceed with stage two.
Macroscopic traffic flow models describe the evolution of aggregated traffic characteristics over time and space, which are required by model-based traffic estimation approaches. Since current first-order Lagrangian macroscopic traffic flow model has some unrealistic implicit assumptions (e.g., infinite acceleration), a second-order Lagrangian macroscopic traffic flow model has been developed by incorporating drivers’ anticipation and reaction delay. A multi-sensor extended Kalman filter (MEKF) algorithm has been developed to combine heterogeneous measurements from multiple sources. A MEKF-based traffic estimator, explicitly using the developed second-order traffic flow model and measurements from loop detectors as well as GPS trajectories for given fractions of vehicles, has been proposed which gives real-time link-level traffic estimates in the bi-level estimation system.
The lane-level estimation in the bi-level data fusion system uses the link-level estimates as priors and adopts a data-driven approach to obtain lane-based estimates, where now heterogeneous multi-sensor measurements are combined using parallel spatial-temporal filters.
Experimental analysis shows that the second-order model can more realistically reproduce real world traffic flow patterns (e.g., stop-and-go waves). The MEKF-based link-level estimator exhibits more accurate results than the estimator that uses only a single data source. Evaluation of the lane-level estimator demonstrates that the proposed new bi-level multi-sensor data fusion system can provide very good estimates of real-time lane-based traffic conditions.
A key issue in using autoencoders for nonlinear variation pattern discovery is to encourage the learning of solutions where each feature represents a unique variation source, which we define as distinct features. This problem of learning distinct features is also referred to as disentangling factors of variation in the representation learning literature. The remainder of this dissertation highlights and provides solutions for this important problem.
An alternating autoencoder training method is presented and a new measure motivated by orthogonal loadings in linear models is proposed to quantify feature distinctness in the nonlinear models. Simulated point cloud data and handwritten digit images illustrate that standard training methods for autoencoders consistently mix the true variation sources in the learned low-dimensional representation, whereas the alternating method produces solutions with more distinct patterns.
Finally, a new regularization method for learning distinct nonlinear features using autoencoders is proposed. Motivated in-part by the properties of linear solutions, a series of learning constraints are implemented via regularization penalties during stochastic gradient descent training. These include the orthogonality of tangent vectors to the manifold, the correlation between learned features, and the distributions of the learned features. This regularized learning approach yields low-dimensional representations which can be better interpreted and used to identify the true sources of variation impacting a high-dimensional feature space. Experimental results demonstrate the effectiveness of this method for nonlinear variation pattern discovery on both simulated and real data sets.