Search Results for design of experiments

This article describes methods that are oriented toward the analysis of planned cooperative experiments that involve multiple factors, blocks, and/or treatment levels. The experiments include factorial, fractional factorial, randomized block, and incomplete block experiments.

Planning of experiments does not consist merely of identifying a few key parameters and then selecting a specific plan. Selection of the proper experimental plan depends on the purpose of the experiment, physical restrictions on the taking of measurements, and other restrictions imposed by time, economic considerations, and materials and personnel availability. This article presents recommendations that should be followed in outlining the methods of conducting and analyzing an experiment to ensure successful results. It discusses restricted type of experiments, in which the experimenter varies the parameters, or factors, under study and then observes the effects of this action. These include factorial experiments, blocked factorial experiments, and fractional factorial experiments. The article describes the estimation of experimental errors and provides information on randomized designs and block designs. It also presents the methods for determining optimum conditions or levels.

When planning a corrosion-testing program, it is advisable to select the testing conditions carefully in order to produce ranking parameters with minimal influence from testing conditions while rich in engineering significance. This article provides a discussion on test objectives, metal composition and metallurgical conditions, test specimen preparation, and corrosion damage assessment. It describes a strategy for planning the design of controlled and uncontrolled factorial experiments. The article contains a table that lists the elements of an iterative process for the experimental design. It illustrates the experimental designs applied to corrosion testing.

This article presents an approach to manage the uncertainty present in materials design. It describes inductive and deductive approaches to deal with uncertainty. The article focuses on providing an understanding of the opportunities for managing uncertainty and the decisions that influence the accuracy of the results. A design of experiments (DOE) represents a sequence of experiments to be performed, expressed in terms of factors set at specified levels. The article discusses the two types of DOEs: the full factorial design and the fractional factorial design. It explains the factors to be considered when selecting a procedure for propagating uncertainty. The article lists the categories of the popular types of uncertainty propagation methods, including simulation-based methods, local expansion methods, and numerical integration-based methods.

Concurrent engineering is product development that is done by concurrently utilizing all of the relevant information in making each decision. This article discusses the three aspects that must be taken into account for all product development decisions. The aspects include product functionality, production capability, and field-support capability. The concurrent process is carried out by a multifunctional team that integrates the specialties. The article schematically illustrates product design team configurations with subsystem teams and team of subsystem leaders. It discusses the three-step decision-making process, such as requirements, concepts, and improvement, followed by multifunctional product development teams. The article describes the two types of requirements development by multifunctional teams, namely, quality function deployment and functional analysis. It schematically illustrates the integration of product requirements and concept development. The article concludes with a discussion on the improvement of concepts in terms of robust design and mistake minimization.

This article discusses statistical concepts that form the basis of most of the following articles on specific areas of applied statistics and data analysis. It reviews some of the basic concepts that must be understood to successfully apply the statistical procedures, including probability, random variables, degrees of freedom, confidence limits and intervals, and reliability. Descriptive statistics, measures of central tendency, confidence limits and intervals, and degrees of freedom are also discussed.

This article describes how design can unfavorably affect product quality. It provides information on the total quality management philosophy, emphasizing the principles of quality management. The article discusses various methods for evaluating a product design for quality. It presents design guidelines that are intended to provide products with a potential for higher levels of quality.

This article addresses problems, such as “in spec” dilemma and on-target key, associated with traditional approaches to quality. It discusses major robust design techniques, tools, and concepts, such as quality loss function, parameter design, tolerance design, signal-to-noise ratio, technology development, and orthogonal arrays.

Thermomechanical are used to gain insight into the causes of problems that arise during a given thermomechanical process. This article provides examples to demonstrate how significant the parameters were selected for specific tests. It examines the types of problems that can occur during a thermomechanical process. The article provides information on the thermophysical properties, which include specific heat, coefficient of thermal expansion, thermal conductivity/diffusivity, and density. It concludes with examples that illustrate how the various considerations in testing are successfully used to solve practical thermomechanical processing problems.

Statistics are extremely important tools in the operation of press shops, providing numerical process analysis capabilities. The most common use of statistics in the press shop is statistical process control (SPC) that uses statistical techniques such as control charts to analyze a process or its output to enable appropriate actions to be taken to achieve and maintain a state of statistical control. This article discusses the role of statistics in sheet metal forming operations, both in terms of SPC techniques, such as control charting, statistical deformation control, and experimental design, including single-variable studies, multivariable studies, and Taguchi experiments.

This article presents the three levels of investigations of distortion engineering. On Level 1, the parameters and variables influencing distortion in every manufacturing step must be identified. More than 200 parameters can affect distortion. The design of experiments approach allows for the investigation of larger numbers of parameters by a limited number of samples, and can be structured into system analysis, test strategy, test procedure, and test evaluation. Level 2 focuses on understanding the distortion mechanisms by using the concept of distortion potential and its carriers. Distortion engineering aims to compensate distortion using the so-called compensation potential (Level 3). Level 3 discusses the measures to improve homogeneity, and respectively the symmetry, of the carriers of the distortion potential. The article also discusses the compensation of the resulting size and shape changes of the existing asymmetries by well-directed insertions of additional inhomogeneity/asymmetries in one or more of the distributions of the carriers.

The heat treatment of steel involves a number of processes (such as stress relieving, normalizing, annealing etc) to condition the microstructure and obtain desired properties. This article discusses typical heat treating process control procedures for carbon and low-alloy steels, as well as the importance of time, and temperature control in heat treatment. Temperature Uniformity Survey, a testing procedure intended to map variations in temperature throughout the furnace work zone, helps in precise control of temperature. The article focuses on the measuring instruments used to determine gas pressure, vacuum level, gas flow, and gas composition. It focuses on their measuring quenchant characteristics, including bulk temperature, viscosity, composition, and cooling efficiency. The article describes the procedures for detecting variability in the incoming product. It presents, through an example, the general application of design of experiments techniques to locate and tune vital process parameters. The devices used in the control process of mechanical components are also reviewed.

The study of the physical properties of ductile solids subjected to shock wave loading is undertaken to understand how the thermodynamic conditions and strain rate affect material response. This article presents a description of a range of possible experimental techniques to quantify the structure/property effects of planar shock waves on ductile materials (metals and alloys) due to the wave propagation through the material. The techniques include explosive-driven shock-loading methods, shock-loading methods using exploding foil and laser-driven impactors, gas/powder launcher-driven shock loading methods, and radiation-driven shock-loading methods. Design parameters for shock recovery fixtures, spallation fixtures, and the flyer-plate experiment, are also discussed.

Additive manufacturing (AM) creates parts layer by layer directly from three-dimensional computer-aided design data. This article discusses systematic ways to address the challenges in AM data integration by exploring various AM-specific data-integration scenarios that can improve the current AM ecosystem. Representative AM data sources are also described. A reference framework that captures the heterogenous AM data sources and existing data-integration mechanisms are used. General data-integration practices—based on existing manufacturing data and lab information system integration experiences—are recommended to automate AM data flow, operations, and development. Lastly, the article discusses the seven steps in the big-data-integration workflow.

Designing composites for structural performance initially involves meeting a set of desired performance specifications at a minimum cost. This article discusses the factors that are considered in designing the manufacturing of polymeric composites. It describes the various aspects of manufacturing, forming process, and post-processing and fabrication for designing the composites.

Gravity has profound influences on most solidification and crystal growth processes. Modification of gravity over practical time scales for the purposes of modifying or controlling solidification proves to be a far more daunting and expensive technological challenge. This article discusses various microgravity solidification experiments that involve pure metals, alloys, and semiconductors and presents the official NASA acronyms for them. MEPHISTO, TEMPUS, the isothermal dendritic growth experiment, and advanced gradient heating facility, are also discussed.