Thomas Hill, Ph.D.; Robert Eames; and Sachin Lahoti’s default image

By Thomas Hill, Ph.D.; Robert Eames; and Sachin Lahoti

Data mining methods have many origins, including drawing on insights into learning as it naturally occurs in humans (cognitive science), and advances in computer science and algorithm design on how to best detect patterns in unstructured data. Although traditional statistical methods for analyzing data, based on statistical theories and models, are now widely accepted throughout various industries, data mining methods have only been widely embraced in business for a decade or two. However, their effectiveness for root cause analysis, and for modeling, optimizing and improving complex processes, are making data mining increasingly popular--and even necessary--in many real-world discrete manufacturing, batch manufacturing, and continuous-process applications.

There is no single, generally agreed-upon definition of data mining. As a practical matter, whenever data describing a process are available, in manufacturing for example, then any systematic review of those data to identify useful patterns, correlations, trends, and so forth, could be called “data mining.” Put simply, data mining uncovers nuggets of information from a sometimes vast repository of data describing the process of interest.

Peter Schulz’s picture

By Peter Schulz

 

The idea of mixing optics and measurement has its origins hundreds of years ago in the realm of pure science, i.e., astronomy (telescopy) and microscopy. Manufacturing first adopted optics for routine inspection and measurement of machined and molded parts in the 1920s with James Hartness’ development of instruments capable of projecting the magnified silhouette of a workpiece onto a ground glass screen. Hartness, as longtime chairman of the United States’ National Screw-Thread Commission, applied his pet interest in optics to the problem of screw-thread inspection. For many years, the Hartness Screw-Thread Comparator was a profitable product for the Jones and Lamson Machine Company, of which Hartness was president.

Horizontal vs. vertical instrument configurations

 

Tom Pyzdek’s picture

By Tom Pyzdek


In 1988, Motorola Corp. became one of the first companies to receive the Malcolm Baldrige National Quality Award. The award strives to identify those  excellent firms that are worthy role models for other businesses. One of Motorola's innovations that attracted a great deal of attention was its Six Sigma program. Six Sigma is, basically, a process quality goal. As such, it falls into the category of a process capability (Cp) technique.

The traditional quality paradigm defined a process as capable if the process's natural spread, plus and minus three sigma, was less than the engineering tolerance. Under the assumption of normality, this translates to a process yield of 99.73 percent. A later refinement considered the process location as well as its spread (Cpk) and tightened the minimum acceptable so that the process was at least four sigma from the nearest engineering requirement. Motorola's Six Sigma asks that processes operate such that the nearest engineering requirement is at least plus or minus six sigma from the process mean.

Motorola's Six Sigma program also applies to attribute data. This is accomplished by converting the Six Sigma requirement to equivalent conformance levels (see Figure 1).

Craig Cochran’s picture

By Craig Cochran

The most significant change in the upcoming revision to ISO 9001 is probably not what you'd expect it to be: It's not customer satisfaction, continual improvement or even the process-model structure of the standard. The most significant change is the requirement for quality objectives. ISO 9001:2000 requires that quality objectives be established at each relevant function and level within the organization (i.e., just about everywhere). The manner in which quality objectives are established and managed will have an enormous impact on the organization's performance. The quality objectives will either drive strategic improvements throughout the organization, significantly elevating the importance of the quality management system, or they'll simply become a meaningless exercise in data collection. It all depends on how the task is carried out.

 The basic requirements for quality objectives are quite simple:

Nicolette Dalpino’s default image

By Nicolette Dalpino

 

What is quality? An academic definition of quality as it relates to business might be that quality is a product or service that consistently has zero defects, conforms to particular specifications, and is satisfactorily received by the customer. Another aspect of quality is that it is a thought process sought out by organizations to create an overall drive toward efficiency, the reduction of waste, and the continual creation of more streamlined management processes.

“Unlike twenty years ago, when the quality department was viewed as the creator of quality, now the whole concept is more ingrained into the culture of organizations,” says Ron Atkinson, past president of the American Society for Quality. “Quality is created by the people performing the function, whether it be assembling a Bluetooth device or filling out an intake form at a medical clinic. Therefore, a culture of quality is emerging in which the leadership of organizations is emphasizing that the functional areas are responsible for quality in the same way that they are responsible for manpower costs, etc.”

Quality Digest’s picture

By Quality Digest

 

Download directory

 

Welcome to Quality Digest’s 2008 Consultants Directory, listing companies that provide quality consulting services.

Check the abbreviation key on page 48 for a preview of the services offered by each company. If additional information was provided to us, you’ll find it online at http://www.qualitydigest.com/content/buyers-guides. As always, we encourage you to contact these companies or visit their web sites.

Quality Digest hasn’t evaluated nor do we endorse any of the following companies listed in this directory.

We wish you well in finding a consultant for your specific needs.

Chris Eckert’s picture

By Chris Eckert

Manufacturers’ efforts to do more with less have resulted in purchasing departments sourcing cheaper products and parts, often from overseas. Such cost-cutting certainly makes purchasing look good to management. But the effect on quality professionals may be just the opposite: product or part defects, malfunctions or undesirable side effects, not to mention the challenge of producing high-quality end-products within narrow timelines and budgets. Many sleepless nights are a frequent outcome.

Because cost cutting and global sourcing are here to stay, how can quality professionals combat these monumental challenges? Root cause analysis (RCA), when fully utilized, can eliminate defects in your operations as well as defects that you inherit from suppliers, ultimately helping to maintain a satisfied and engaged customer base.

Terri D. Lind’s picture

By Terri D. Lind

Energy generation is a multifaceted industry comprising dozens of major discrete technologies and thousands of companies. For reasons that are at once political, economic, and environmental, the energy industry occupies a central place in modern human society, and it will for the foreseeable future.

Alternative energy resources, such as photovoltaic modules and wind turbines, represent a particularly fast-growing segment of the industry. This article will look at this sector from the perspective of quality assurance and safety testing, two extremely important concerns for producers, as well as consumers, of alternative energy.

Craig Cochran’s picture

By Craig Cochran


Because information in document form drives nearly every action in any organization, the ability to control this information usually means the difference between success and failure. Thus, document control remains the single most critical quality assurance discipline. As with many other systems, document control is more successful if it's simple, intuitive and user-friendly. And the first step toward this end is deciding exactly which documents need to be controlled.

Documents requiring control

 "Do I need to control this document?" is one of the most frequently asked questions in organizations working toward, or maintaining, a formal management system. Given the universe of documents possibly requiring control, the question is understandable. Besides, most people would rather not control a document if they don't have to.

 The ISO 9001:2000 standard provides a quick answer to the question of what must be controlled. The first sentence of section 4.2.3 on document control states, "All documents required by the quality management system shall be controlled." This means that if a document addresses or relates to any of the issues in ISO 9001:2000, it must be controlled. Here are some questions to ask when determining whether a document should be controlled:

Paul W. Ingallinera’s default image

By Paul W. Ingallinera

Imagine that you oversee the quality control department for a small lug nut manufacturer that supplies the major U.S. automakers. One night, as you're watching the news, the station features a story about a car that lost one of its wheels while traveling more than 55 miles per hour. The car hit a guard rail, and all persons in the vehicle were badly injured. The ensuing investigation determines that the wheel failed because its lug nuts sheered off.

The problem ultimately is traced to a torque wrench, used during the lug nut manufacturer's final inspection, that hadn't been calibrated in more than 10 years. Consequently, it displayed incorrect torque values. You can't understand how this could have happened because your company is registered to ISO 9000 and recently achieved QS-9000 compliance. Upon reflection, however, you realize that the wrench never was entered into the calibration system and therefore never addressed during the audit.