Operations Research, Systems Engineering and Industrial Engineering Commons^™

Multivariate Time Series Classification Of Sensor Data From An Industrial Drying Hopper: A Deep Learning Approach, Md Mushfiqur Rahman

Graduate Theses, Dissertations, and Problem Reports

In recent years, the advancement of industry 4.0 and smart manufacturing has made a large number of industrial process data attainable with the use of sensors installed in the machineries. This thesis proposes an experimental predictive maintenance framework for an industrial drying hopper so that it can detect any unusual event in the hopper which reduces the risk of erroneous fault diagnosis in the manufacturing shop floor. The experimental framework uses Deep Learning (DL) algorithms in order to classify Multivariate Time Series (MTS) data into two categories- failure or unusual events and regular events, thus formulating the problem as binary …

Methodology To Qualify And Monitor A Chemically Bonded Sand System Used In Foundries, Prayag Pravinbhai Patel

Dissertations

The goal of this dissertation is to establish a new quality control framework that combines a statistical process control (SPC) approach to casting quality for chemically bonded sand systems used in foundries. Foundries in the United States use the American Foundry Society standardized sand testing to monitor chemically bonded sand systems. These standardized tests are inefficient for two reasons. Firstly, standard tests are based on mechanical, physical, chemical and thermal properties of a sand system that do not consider interaction between these properties, but sand casting processes are inherently thermo-mechanical, thermo-chemical and thermo-physical. Secondly, these tests can only detect large …

Grouping Techniques To Manage Large-Scale Multi-Item Multi-Echelon Inventory Systems, Anvar Abaydulla

Graduate Theses and Dissertations

Large retail companies operate large-scale systems which may consist of thousands of stores. These retail stores and their suppliers, such as warehouses and manufacturers, form a large-scale multi-item multi-echelon inventory supply network. Operations of this kind of inventory system require a large number of human resources, computing capacity, etc.

In this research, three kinds of grouping techniques are investigated to make the large-scale inventory system “easier” to manage. The first grouping technique is a network based ABC classification method. A new classification criterion is developed so that the inventory network characteristics are included in the classification process, and this criterion …

Human Performance Engineering Approach, Dotan I. Shvorin

Dr. Dotan Shvorin

Cost-Sensitive Learning-Based Methods For Imbalanced Classification Problems With Applications, Talayeh Razzaghi

Electronic Theses and Dissertations

Analysis and predictive modeling of massive datasets is an extremely significant problem that arises in many practical applications. The task of predictive modeling becomes even more challenging when data are imperfect or uncertain. The real data are frequently affected by outliers, uncertain labels, and uneven distribution of classes (imbalanced data). Such uncertainties create bias and make predictive modeling an even more difficult task. In the present work, we introduce a cost-sensitive learning method (CSL) to deal with the classification of imperfect data. Typically, most traditional approaches for classification demonstrate poor performance in an environment with imperfect data. We propose the …

Kernel-Based Data Mining Approach With Variable Selection For Nonlinear High-Dimensional Data, Seung Hyun Baek

Doctoral Dissertations

In statistical data mining research, datasets often have nonlinearity and high-dimensionality. It has become difficult to analyze such datasets in a comprehensive manner using traditional statistical methodologies. Kernel-based data mining is one of the most effective statistical methodologies to investigate a variety of problems in areas including pattern recognition, machine learning, bioinformatics, chemometrics, and statistics. In particular, statistically-sophisticated procedures that emphasize the reliability of results and computational efficiency are required for the analysis of high-dimensional data. In this dissertation, first, a novel wrapper method called SVM-ICOMP-RFE based on hybridized support vector machine (SVM) and recursive feature elimination (RFE) with information-theoretic …