More companies are leveraging high speed vision systems to inspect their products. This testing directly on the line is a major advancement in inspection and measurement methods. Automation allows data to be collected quickly and efficiently and 100% inspection becomes feasible. A common question that arises is, "Does my 100% automatic inspection system replace the need for Statistical Process Control?". (By Steven Wachs, Principal Statistician, Integral Concepts.)
Most quality professionals are familiar with basic hypothesis tests such as the 2-sample t test. However, depending on the goals of the study, another type of test, called an equivalence test, may be utilized instead of traditional hypothesis tests. This article will review statistical hypothesis testing in general and then introduce equivalence testing and its application. To illustrate the differences between traditional hypothesis tests and equivalence tests, we will focus on the case of comparing 2 independent samples. The concepts may be easily extended to other situations (such as comparing a sample to a target or paired comparisons). (By Steven Wachs, Principal Statistician, Integral Concepts.)
When Statistical Process Control is applied properly, tremendous benefits in profitability and process understanding are achieved. SPC can prevent problems—saving companies millions of dollars that otherwise would have been paid or lost in scrap, rework, warranty, litigation, and market share decline. In addition, SPC data has other, less commonly recognized uses that can empower manufacturing. Other benefits from SPC data include efficient problem resolution, performance prediction, machine and tooling reliability, comparisons of processes/groups, and feedback to engineering/R&D. (By Allise Wachs, Ph.D., Integral Concepts.)
So how does process control (or the lack of it) affect product reliability? Reliability is defined as the probability that a material, component, or system will perform its intended function under defined operating conditions for a specified period of time. (By Steven Wachs, Principal Statistician, Integral Concepts.)
Consistent overfilling to minimize risk is inefficient and sacrifices profitability, while aggressive filling practices result in significant risks of non-compliance with net contents regulations leading to potential penalties, loss of reputation, and impaired customer relations. Statistical process control and process capability methods may be utilized to determine optimal targets for product fill weights or volumes for a given process.
A common problem in complex manufacturing is the cost of having variation in the manufacturing process. In the case study presented here, we were brought in to address problems stemming from variation in a process that had been costing the manufacturer $1.2 million annually. Using statistical methods, we were able to identify and resolve the issue in four days. (By Steven Wachs, Principal Statistician and Allise Wachs, Ph.D.)
Recent news offers a reminder that huge opportunities still exist to prevent or reduce warranty costs that drain manufacturers’ bottom lines.
Traditional SPC methods were developed to support high volume production and long production runs. However, with the trend toward product specialization, product diversity, and flexible manufacturing, short production runs have become more common. Applying SPC in the traditional manner presents challenges in short production runs because by the time enough datails are collected to establish valid control charts, the production run may be over.
In last month’s article, we introduced the concept of utilizing Deviation from Nominal (DNOM) control charts for short production runs. These charts allow us to monitor process characteristics over time even when the units being controlled have varying nominal values. DNOM charts assume that the process variability (i.e. standard deviation) does not vary significantly by part type. However, often this assumption does not hold. Characteristics with larger nominal values tend to have more variation than characteristics with smaller nominal values. This month we discuss how to test whether or not significant differences in variability exist and if so, how to modify the DNOM methods and charts to handle this situation.
Many advocate the replacement of SPC with more simplistic approaches such as "Pre-Control." Unfortunately, in a manufacturing world of increasing complexity, and with a global market demanding the highest quality and reliability, applying "simple" tools at the expense tools with considerably more value (and really not very complex or difficult) doesn't cut it.
Control charting captures snapshots of the process average and variation over time. When specific signals are observed on the control charts, we conclude that the process is unstable because the probability of observing those signals if the process had not changed is very small.
Many factors should be considered when choosing a control chart for a given application.
The key is to specify a subgroup size so that significant shifts are detected with high probability and that insignificant shifts are unlikely to produce a signal.
Last month’s article focused on the conceptual application of appropriate sample sizes for X-bar charts. This month we describe the sample size formula and its application in detail.
Most manufacturers would rate product quality as a key driver of their overall ability to satisfy customers and compete in a global market.
Clearly, controlling everything is not feasible or a smart use of limited resources.
Nothing and everything. Though they are not directly linked, statistician and SPC expert Steven Wachs cautions that without evidence of process stability, capability data is useless.
In my last column, I was asked about a capability index called Cpk. Cpk is a measure of a process' ability to conform to specification. A Cpk = 1 means that if nothing changes, 99.73% of the process output will be within specification, as in Figure 1.
Ask people involved with the design and manufacture of a product the following question: "What is Quality?" Many, if not most, of the responses will be some form of the following: "Quality is ensuring that our products meet the customer (or engineering) specifications. Unfortunately, this leads to a "conformance to specifications" or a "Product Control" approach to quality.
Just like control charts tell us about the stability of the process, capability analyses tell us about process capability.