Measuring Process Capability Research Articles

Validating the ISO/IEC 15504 measures of software development process capability

ISO/IEC 15504 is an emerging international standard on software process assessment. It defines a number of software engineering processes, and a scale for measuring their capability. A basic premise of the measurement scale is that higher process capability is associated with better project performance (i.e., predictive validity). This paper describes an empirical study that evaluates the predictive validity of the capability measures of the ISO/IEC 15504 software development processes (i.e., develop software design, implement software design, and integrate and test). Assessments using ISO/IEC 15504 were conducted on projects world-wide over a period of two years. Performance measures on each project were also collected using questionnaires, such as the ability to meet budget commitments and staff productivity. The results provide evidence of predictive validity for the development process capability measures used in ISO/IEC 15504 for large organizations (defined as having more than 50 IT staff). Furthermore, it was found that the “Develop Software Design” process was associated with most project performance measures. For small organizations evidence of predictive validity was rather weak. This can be interpreted in a number of different ways: that the measures of capability are not suitable for small organizations, or that software development process capability has less effect on project performance for small organizations.

Quality technique transfer: Manufacturing and software

An argument for quality technique transfer between manufacturing and software is put forward in which it is recognised that the nature of the production process differs and that the emphasis accorded given stages in the respective life cycles may also differ. The relevant issues that contribute to successful transfer are discussed before a case is made for potential candidate techniques from manufacturing, electronics, and avionics. A common feature of the underlying analysis is identified as an increase in the emphasis placed on quantitative approaches. The paper then proceeds to explain the example techniques which are: the manufacturing process capability measures for Statistical Process Control (SPC); Taguchi Fractional Factorial Experiments; built in testing from VLSI technology; and Black Box recording, derived from avionics, in usage testing. Instances of the implementation of each are given and it is concluded that practical implementations of transferred techniques are related to: the product development phase; the maintenance phase; and the process improvement sphere. The strength of pressures to overcome existing product deficiencies are reasoned to mitigate implementation costs.

A generalization of Clements’ method for non‐normal Pearsonian processes with asymmetric tolerances

For non‐normal Pearsonian processes, Clements proposed a method for calculating estimators of the two basic process capability indices Cp and Cpk. Pearn and Kotz applied Clements’ method to obtain estimators for the other two more advanced process capability indices Cpm and Cpmk. Their considerations on those indices, however, are restricted to processes with symmetric tolerances. Recently, Pearn and Chen proposed a generalization of the index Cpk to handle cases with asymmetric tolerances. The generalization takes into account the asymmetry of the manufacturing specifications, which is shown to be superior to the other existing methods. In this paper, we apply this approach and consider a generalization of Clements’ method for non‐normal Pearsonian processes where the manufacturing tolerances are asymmetric. Comparisons between the original Clements’ method and the proposed generalization are provided. The results indicate that the generalization is more accurate than the original Clements’ method in measuring process capability.

The effect of skewness on estimates of some process capability indices

The use of process capability indices, which are statistical measures of process capability, is based on several assumptions. For instance, the process monitored is supposed to be stable and the process output should be approximately normally distributed. These assumptions are not always fulfilled in practice. This article focuses on the problem when the process monitored has an output which is non-normally distributed. After presenting a short literature review on research concerning process capability indices and non-normal distributions, the effect of skewness on estimates of process capability indices is studied using a simulation study based on lognormally distributed process outputs. It is found that the effect of skewness is relatively systematic. From the study it is clear that the effect of skewness on estimates of process capability indices is so severe that it has to be considered when studying the capability of a process. Otherwise, erroneous decisions might be made when improving the process studied. It is suggested that further research, for instance, focusing on correction-factors to use when the process output has different skew shapes might be meaningful. However, research focusing on totally new ways of estimating process capability is primarily encouraged.

A review and interpretations of process capability indices

Practitioners of industrial statistics are generally familiar with the common C p and C pk process capability indices. However, many additional indices have been proposed, and knowledge of these is less widespread. More importantly, information regarding the indices' comparative behavior is lacking. This paper compares the behavior of various indices under shifting process conditions. Both useful and misleading characteristics of the indices are identified. We begin with a short history of process capability measures. Several process capability indices are reviewed. Application areas for capability indices are also summarized. The indices are grouped according to the loss functions which are used in their interpretation. Characteristics of the various indices are discussed. Finally, recommendations are made for selection of indices at differing levels of process performance.

Process capability measurement of frequent replacement spherical soft contact lenses

Frequent replacement soft contact lenses must have good reproducibility in order to avoid clinical problems arisingfrom manufacturing variations in lens parameters. This study assessed the actual and potential process capability of eight frequent replacement lenses (monthly or 2-weekly replacement) in relation to back vertex power, back optic zone radius, total diameter and centre thickness. Twenty-four lenses in three powers (−1.00, −3.00, −6.00 D) were measured for eightfrequent replacement lenses: Acuvue, Acuvue 2, Biomedics 55, Encore, Focus, Optima FW, Softens 66, Surevue. In general, the lenses showed adequate reproducibility in respect of those parameters likely to affect lens fit, namely back optic zone radius, total diameter and centre thickness. The process capability results showed some variation in reproducibility of BVP between lens types and between lens powers. Process capability was found to be a useful measure of contact lens reproducibility.

Measuring Process Capability

Measuring Process Capability

Measuring process capability: Techniques and calculations for quality and manufacturing engineers

This guide to process capability measurement includes procedures for identifying critical characteristics, and shows how to establish reasonable process and machine capability goals. Real-life case studies illustrate how capability measures should be analyzed and interpreted.

Capability indices for non-normal distributions with an application in electrolytic capacitor manufacturing

Process capability indices C p( u, v), which include the four basic indices C p, C pk, C pm and C pmk as special cases, have been proposed to measure process potential and performance. C p( u, v) are appropriate indices for processes with normal distributions, but have been shown to be inappropriate for processes with non-normal distributions. In this paper, we first consider two generalizations of C p( u, v), which we refer to as C Np( u, v) and C′ Np( u, v), to cover cases where the underlying distributions may not be normal. Comparisons between C Np( u, v) and C′ Np( u, v) are provided. The results indicated that the generalizations C Np( u, v) are superior to C′ Np( u, v) in measuring process capability. We then present a case study on an aluminum electrolytic-capacitor manufacturing process to illustrate how the generalizations C Np( u, v) may be applied to actual data collected from the factories.

An application of non-normal process capability indices

Numerous process capability indices, including Cp, Cpk, Cpm, and Cpmk, have been proposed to provide measures of process potential and performance. In this paper, we consider some generalizations of these four basic indices to cover non-normal distributions. The proposed generalizations are compared with the four basic indices. The results show that the proposed generalizations are more accurate than those basic indices and other generalizations in measuring process capability. We also consider an estimation method based on sample percentiles to calculate the proposed generalizations, and give an example to illustrate how we apply the proposed generalizations to actual data collected from the factory. © 1997 John Wiley & Sons, Ltd.

A process capability index with reliable confidence intervals

A well-know process capability index is slightly modified in this article to provide a new measure of process capability which takes account of the process location and variability, and for which point estimator and confidence intervals do exist that are insensitive to departures from the assumption of normal variability. Two examples of applications based on real data are presented.

Statistical process control of an industrial process in real time

Most of the real-time industrial control methods suffer from the fact that the corrective action is often taken after the instability has been detected, In other words the control strategy has always to catch-up with the problems by bringing the process back to optimum condition. Most of the time correct assignable cause of variation is not known. The conventional methods of quality control are always to catch-up with the product quality. In addition to this, conventional methods may cause financial losses due to machinery downtime and in many cases may not be able to predict the problem to avoid machinery downtime. The new computer-aided statistical process control (SPC) provides several windows in to the industrial process. These windows help collect statistical information which in turn can be used to find assignable causes of variation in product quality, quantitative measure of process capability, presence of extraneous influences and deterioration of certain equipment. We have introduced various types of problems into the industrial grade process control system and by using the SPC software tool we have collected data samples of the variables over time. These data sample were used to generate control charts of various process variables during runtime. Later, by analyzing the trend of the control charts we have been able to relate back to the problems which were originally introduced in to the process.

Choice of inspection strategy using quality simulation

The effects of the choice of inspection level are poorly understood by many manufacturing companies and frequently result in waste or customer dissatisfaction. Describes the use of a quality simulation technique to generate cost data related to manufacturing quality performance and inspection strategies. Reviews underlying ideas concerning quality characteristics, process capability and quality performance measures and describes the simulation assumptions and technique. Presents simulation results which show the quality‐related costs associated with various inspection strategies for a range of quality performance.

AIRCRAFT ACQUISITION AND OPERATION IN A TOTAL QUALITY ENVIRONMENT Part II: Process Modeling and Improvement

In part I of this work, a conceptual framework and approach for handling the problem of aircraft acquisition and operation in a total quality environment was presented. Decisions related to aircraft acquisition or operation are usually based on predicting the expected performance of Aircraft Mission Support Process (AMSP). The objective of part II is to present the modeling approach and improvement procedure of this process. The model is developed such that it can provide sampling experiments required for the application of Statistical Process Control (SPC) and process capability measures. A process capability index is used to measure the capability of the process in providing the system user with the required level of performance. Aircraft operational availability is taken as the process external performance indicator (or quality characteristic). A simple analytical model is investigated to determine its adequacy for the intended statistical analysis. Simulation is adopted as the preferred approach to model the process. Different acquisition options for improvement are evaluated by changing the design, support, and/or operational characteristics of the acquired system. For each option it is possible to determine the benefit and the worth of the change. Results of application of this approach show its power in predicting the process future performance. The suggested model could also provide an interfacing mechanism between aircraft users and suppliers in support of their mutual decision making during aircraft acquisition or operation.

AIRCRAFT ACQUISITION AND OPERATION IN A TOTAL QUALITY ENVIRONMENT Part I: A Conceptual Framework and Approach

A conceptual framework and an approach for handling the problem of aircraft acquisition and operation in a total quality environment are proposed in this part of the work. For this purpose, a typical acquisition process is described and the system operational and maintenance support requirements are summarized. The Aircraft Mission Support Process (AMSP) is analyzed at different levels of detail to identify the problem symptoms, causes, statement, problem solving approach and the design alternatives. This provides the necessary background and foundation for establishing a Logistic Engineering Model to support the decision making during aircraft acquisition and operation. Statistical Process Control (SPC) and process capability measures are utilized in the decision making process. To support this concept, the intended model is further developed to provide sampling experiments to pursue the required statistical analysis. This is done by using aircraft operational availability as the external performance indicator for the Aircraft Mission Support Process. Internal performance indicators are also considered. This approach can provide a mechanism for evaluation of different acquisition and/or operation options directed to continuous improvement of aircraft readiness and utilization. Part II of this work presents (AMSP) modeling and improvement procedure.

The role of NDE in predicting residual life for aircraft engine components

This paper outlines major changes which have occurred in the methods used for predicting the residual life of cyclically stressed critical rotating elements of aircraft engines, and the consequent increased importance of quantifying the performance of NDE processes through measurement of the probability of detection. Both industrial companies and government agencies have expended considerable efforts on defining methods of measurement of inspection process capability, on reviewing statistical techniques for their analysis, and on development of automated inspection systems to provide the enhanced sensitivity and reliability necessary for the detection of flaws of size relevant to damage-tolerant life management of fracture-critical components. The increasingly global nature of both military and civil aviation industries makes these programmes of international interest.

Application of Systematic Error Bounds to Detection Limits for Practical Counting

Overly optimistic estimates of detection limits can result in the use of unrealistic conservatism for decisions about the presence of activity. In some practical counting situations, overly conservative detection limits can result in economically impractical actions. To help preclude such actions, systematic error bounds, uncertainties, and confidence levels can be used when determining critical levels (Lc), detection limits (Ld), and minimum detectable concentrations. This note discusses the selection of such error bounds and the development of detection limit parameters for practical applications. These parameters are shown to be successfully employed in sample activity and measurement process capability decisions for typical counting instruments.

A process capability indicator

A new measure of process capability, called process capability indicator and denoted by C1is proposed. It is of the form C1=deviation indicator (DI)+w×variation indicator (VI), where DI and VI, are, respectively, measures of the deviation of the process mean from the target value and the process variation, and both are relative to the tolerance. The weight factor w is used for deciding whether more emphasis should be put on VI (large w value) or on DI (small w value). Furthermore, by considering C1as a function of w, it has a spectrum of values which could provide more comprehensive comparison of different processes or measurement of the quality improvement of a process through several stages.

Standard bootstrap confidence interval estimates of CPK

The interpretation of CPK, a common measure of process capability and confidence limits for it, is based on the assumption that the process is normally distributed. The non-parametric but computer intensive method called Bootstrap is utilized and the Standard confidence interval estimate for CPK is calculated. An initial simulation of two processes (one normal and the other highly skewed) is presented and discussed.

A mulvariate measure of process Capability

AbstractA measure of process capability for the multivariate normal case is proposed. This measure takes into account both proximity to the target and the variation observed in the process. The result is analogous to the univariate measure of process capability referred to as Cpm. Some statistical properties associated with the measure are examined. Multivariate specification limits and their creation are also discussed.