Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

This thesis deals with the development of a model-based adaptive test design strategy with a focus on steady-state combustion engine calibration. The first research topic investigates the question how to handle limits in the input domain during an adaptive test design procedure. The second area of scope aims at identifying the test design method providing the best model quality improvement in terms of overall model prediction error. To consider restricted areas in the input domain, a convex hull-based solution involving a convex cone algorithm is developed, the outcome of which serves as a boundary model for a test point search. A solution is derived to enable the application of the boundary model to high-dimensional problems without calculating the exact convex hull and cones. Furthermore, different data-driven engine modeling methods are compared, resulting in the Gaussian process model as the most suitable one for a model-based calibration. To determine an appropriate test design method for a Gaussian process model application, two new strategies are developed and compared to state-of-the-art methods. A simulation-based study shows the most benefit applying a modified mutual information test design, followed by a newly developed relevance-based test design with less computational effort. The boundary model and the relevance-based test design are integrated into a multicriterial test design strategy that is tailored to match the requirements of combustion engine test bench measurements. A simulation-based study with seven and nine input parameters and four outputs each offered an average model quality improvement of 36 % and an average measured input area volume increase of 65 % compared to a non-adaptive space-filling test design. The multicriterial test design was applied to a test bench measurement with seven inputs for verification. Compared to a space-filling test design measurement, the improvement could be confirmed with an average model quality increase of 17 % over eight outputs and a 34 % larger measured input area.

design of experiments; adaptive test design; boundary search

Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

This thesis deals with the development of a model-based adaptive test design strategy with a focus on steady-state combustion engine calibration. The first research topic investigates the question how to handle limits in the input domain during an adaptive test design procedure. The second area of scope aims at identifying the test design method providing the best model quality improvement in terms of overall model prediction error. To consider restricted areas in the input domain, a convex hull-based solution involving a convex cone algorithm is developed, the outcome of which serves as a boundary model for a test point search. A solution is derived to enable the application of the boundary model to high-dimensional problems without calculating the exact convex hull and cones. Furthermore, different data-driven engine modeling methods are compared, resulting in the Gaussian process model as the most suitable one for a model-based calibration. To determine an appropriate test design method for a Gaussian process model application, two new strategies are developed and compared to state-of-the-art methods. A simulation-based study shows the most benefit applying a modified mutual information test design, followed by a newly developed relevance-based test design with less computational effort. The boundary model and the relevance-based test design are integrated into a multicriterial test design strategy that is tailored to match the requirements of combustion engine test bench measurements. A simulation-based study with seven and nine input parameters and four outputs each offered an average model quality improvement of 36 % and an average measured input area volume increase of 65 % compared to a non-adaptive space-filling test design. The multicriterial test design was applied to a test bench measurement with seven inputs for verification. Compared to a space-filling test design measurement, the improvement could be confirmed with an average model quality increase of 17 % over eight outputs and a 34 % larger measured input area.

Engineering measurement & calibration --- Energy technology & engineering --- design of experiments; adaptive test design; boundary search --- design of experiments; adaptive test design; boundary search

Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

This revised book provides an accessible presentation of concepts from probability theory, statistical methods, the design of experiments, and statistical quality control. It is shaped by the experience of the two teachers teaching statistical methods and concepts to engineering students. Practical examples and end-of-chapter exercises are the highlights of the text, as they are purposely selected from different fields. Statistical principles discussed in the book have a great relevance in several disciplines like economics, commerce, engineering, medicine, health care, agriculture, biochemistry, and textiles to mention a few. Organised into 16 chapters, the revised book discusses four major topics—probability theory, statistical methods, the design of experiments, and statistical quality control. A large number of students with varied disciplinary backgrounds need a course in basics of statistics, the design of experiments and statistical quality control at an introductory level to pursue their discipline of interest. No previous knowledge of probability or statistics is assumed, but an understanding of calculus is a prerequisite. The whole book also serves as a master level introductory course in all the three topics, as required in textile engineering or industrial engineering.

Statistics. --- Probabilities. --- Experimental design. --- Statistical Theory and Methods. --- Probability Theory. --- Design of Experiments. --- Mathematical statistics.

Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

The development of international trade is directly connected to the shipbuilding industry. That means that, economically, ships have great value for the world’s trade, as many goods are transported by ships. Thus, the ship’s quality plays a crucial part in the functioning of the system, not only for trade but also for offshore uses, cruises, and fishing activities. In shipbuilding industry, several criteria affect the performance of a shipyard and the vessels themselves, from material’s choice, going through the construction process, until the delivery of the ship. Structure deformation is one of the biggest issues faced by the shipbuilding industry because it is extremely dependent on welded structures and equipment. The consequences of the deformation in ship structures are costly (maintenance, replacement, shorter lifetime) along with customer dissatisfaction and the inefficiency of the hull, especially for ships, where the contractual penalty is very high. As deformations are mainly caused by the welding process, it is important to study the effect of its parameters, considering the material, weld joint, welding type - Submerged Arc Welding (SAW), Flux- Cored Arc Welding (FCAW) – and its welding sequence. Accordingly, to perceive the welding behavior at the workshop and its deformation, welding procedure of the stainless steel AISI 316L was followed and deformations after butt welds, fillet welds and straightening were measured using a tachometer. These measurements were done on the decks of two fishing vessel’s projects - NB 395 and NB 396. In this work, the biggest challenge was to deal with stainless steel AISI 316L, as its use is not conventional for the ship industry. Further, welding type FCAW still need to be fully developed even though; gas electric arc welding principle is the most common in the industry. The design of experiments was performed in spite of confronting numerical analysis with experimental results. By using the diagnosis of the construction process and welding procedure, different assumptions were made in pursuance of improvement of the activities aiming high quality of services, consequently achieving a better quality of delivered vessels

Welding. Deformation. Measurements. Design of Experiments --- Ingénierie, informatique & technologie > Ingénierie civile

Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

This book covers topics in 2 parts: 1) Review of FDA Guidance, 2) Novel Designs and Analyses. While covering basic principles of dose finding, this book details advancements made in drug development. Finding the right dose(s) is one of the most important objectives in new drug development. In Phase I clinical development, one of the objectives is to escalate test doses from low to high. The low doses should be safe, then escalate up to the maximally tolerable dose (MTD). Phase Ⅱ clinical trials then lower test doses to the minimal efficacious dose (MinED). Dose range of a study drug can be thought of as the doses between MinED and MTD. From this dose range, one or a few doses are selected for Phase Ⅲ confirmation. In practice, dose finding is a very difficult in every phase of clinical development for new drugs. The editors brought distinguished researchers and practitioners in biopharmaceuticals and universities, to discuss the statistical procedures, useful methods, and their novel applications in dose finding. The chapters in the book present emerging topics in dose-finding and related interdisciplinary areas. This timely book is a valuable resource to stimulate the development of this growing and exciting field in drug development. .

Biometry. --- Experimental design. --- Data mining. --- Biostatistics. --- Design of Experiments. --- Data Mining and Knowledge Discovery.