Statistical Process Control (SPC)

Statistical Process Control can processes are identified and addressed using the technique. Practices that help establish clear goals and decision points, and are based on meaningful metrics and attributes based on specific program or technical goals, stand to gain the most payback from using SPC. SPC techniques need not be restricted to the present, i.e., planning for the insertion of new technology later in the life cycle should also plan for the use of SPC to ensure that processes are controlled and reliability of the resulting software artifacts is optimized.

Statistical Process Control Statistical process control, or SPC, is a fundamental approach to quality control and improvement that is based on objective data and analysis. The origin of SPC dates back to the 1920s and 1930s at the Western Electric Company and Bell Telephone Laboratories. Walter Shewhart (1891-1967) recognized that variation in a production process can be understood and controlled through the use of statistical methods. He pioneered the use of statistical methods as a tool to manage and control production. Over the next several decades, these tools were taught to engineers and production personnel throughout American industry. The need for higher-quality production to support the defense industry during World War II gave a boost to the use of SPC.

Any method that seeks to avoid the use of transformation for non-normal data requires techniques for identification of the appropriate distributions. In cases where the appropriate distributions are known it is often intractable to implement. This research is concerned with statistical process control (SPC), where SPC can be apply for variable and attribute data. The objective of SPC is to control a process in an ideal situation with respect to a particular product specification. One of the several measurement tools of SPC is control chart. This research is mainly concerned with control chart which monitors process and quality improvement. We believe, it is a useful process monitoring technique when a source of variability is present. Here, control charts provides a signal that the process must be investigated.

In this era of strains on the resources and rising costs of manufacturing, it becomes increasingly apparent that decisions must be made on facts, not just opinions. Consequently, data must be gathered and analyzed. This is where statistical process control (SPC) comes in. For over 70 years, the manufacturing arena has benefited from the tools of SPC that have helped guide the decision-making process. In particular, the control chart has helped determine whether special-cause variation is present implying that action needs to be taken to either eliminate that cause if it has a detrimental effect on the process or to make it standard operating procedure if that cause has a beneficial effect on the process. If no special-cause variation is found to be present, SPC helps define the capability of the stable process to judge whether it is operating at an acceptable level.

1 Introduction In this modern era of constraints on resources and costs of manufacturing products and rendering services, it becomes increasingly significant to make decisions based on facts and not just opinion. Consequently, data must be collected and analyzed. This is the role of Statistical Process Control Tools (SPC Tools). For more than eight (8) decades, industries have been continuously gathering the fruit of success the application of these tools have given them. SPC Tools aim to reduce the variability in aspects of the business concerned such as processes, products and services. These tools helped them in collecting data needed to be improved, analysis of how the data affects the processes, products and services, what are the causes of variations in the key input and output variables and improve those in order to attain controllability and sustain stability.

The aim of statistical process control (SPC) is to center process results around the desired value and to keep the process d isp ersio n w ithin specification. In this context of centring one could speak of the process as being controlled. If all process results lie within the six times standard deviation range the process is considered capable. Process corrections will take place, if there are deviations from the to lerate d process range caused by disturbances. Mostly Shewhart control charts and acceptance control charts are in common use [1] and [3], Shewhart control charts are focused on the desired values while acceptance control charts control predefined limits. Both types are based on a process control range o f 99.73 % of all values within the control limits. The process control procedure would be something like the following scheme for Shewhart control charts [2]:

Dr. D. R. Prajapati [6] (2012) found that statistical process control (SPC) techniques in the automotive industry is offering customers the widest and latest range of sealing solutions. SPC analysis may easily help in improving the efficiency of the manufacturing process thus decreasing the number of defective products, thus saving a lot of re-work cost and valuable time. For each specific product the suggested preventions can considerably decrease the loss to the industry in terms of both money and time. Although, improvement in rejection level of all the other products of the industry is noticed, shocker seals were the main concern because the rejection level of this product was more than 9.1%. After implementing the required suggestions /recommendations for shocker seals, it is found that process capability is improved and it is greater than required.

Keywords— Statistical process control, Control chart, chart and chart I. I NTRODUCTION UALITY control (QC) is an important function in factory as it deals with product inspection before the product was shipped to customers. Statistical process control (SPC) is one of the tools widely used in QC to monitor whether the production process is in control through the use of statistical control chart. This paper focused on the implementation of SPC in the case study company which is a manufacturer of electronics parts. A particular product investigated was the metal frame for actuator which is a critical part in hard disk drive product. SPC in the case study company is currently implemented using commercial software package. This software is used to analyse production process data with control chart and histogram. However, only a few computers are installed with this software because software license is expensive. Moreover, the commercial software is not design specifically to the process hence sometimes difficult for the operator with limit knowledge of SPC. This research aims to develop software for control chart and histogram analysis that designed specifically to previously mentioned process by using Visual Basic. This software helps operators in quality

ABSTRACT Software is the only man made Omni Present system contributing immensely providing complex and critical services to mankind. It’s increasing popularity and usefulness enforces us to measure the software quality. In this paper Time domain failure data is applied to Statistical Process Control(SPC) method to monitor the quality of a software system. We propose a Statistical Control Method over the cumulative quantity between observations of time domain failure data using mean value function of an Non Homogeneous Poisson Process(NHPP) based Logarithmic Poisson Execution Time Model(LPETM).Maximum Likelihood estimation(MLE) is used to estimate the unknown parameters of proposed model.The SPC method employs LPETM to construct the control limits. Two failure data sets are used.

The second idea is that of data mining – extracting information from historical data and trends – that allows process optimization. Often we find unexpected relationships, and can then make better informed decisions. The field of SPC has grown from those simple ideas to today’s software systems that help industry run based on those mathematics. I have put such systems into many foundries in the USA, Germany, and Australia, and they certainly improve the product and reduce cost when properly used. Our statistical package named Graphic Statistical Process Control or GSPC, and that is the topic of this month’s eLetter.

Control charts are widely used in industry as a tool to monitor process characteristics. Deviations from process targets can be detected based on evidence statistical significance. It can be said that the birth of modern statistical process control (SPC) took place when Walter A. Shewart developed the concept of a control chart en 1920’s.Traditional attribute chart such as p and c charts are not suitable in automated high yield manufacturing and continuos production processes. Failure in the selection of the underlying distribution can result incorrect conclusions regarding the statistical control of a process. Traditionally, standard statistical control charts for a discrete random are based on Poisson or binomial distributions. This paper presents the latest development of statistical control charts for a shifted geometric distribution.

In the field of software engineering, we cannot control what is not measured. As a result of this, many statistical techniques such statistical process control (SPC) plays a very important role in managing and controlling these attributes. In other words, control charts of SPC can help us to determine whether a process is under control or not by calculating the control limits so as to visualize the process behaviour over time. As a result of this, many researchers shared their experience on implementing this quantitative technique within software domain.

5. CONCLUSIONS This paper represents an experience report on defining and carrying out a systematic review on Statistical Process Control, which is well known in manufacturing contexts but only recently of interest within the software application domain. As so, we have addressed the issue whether SPC is being correctly applied in software production or not. Answers to our research questions have been assessed through a protocol defined according to guidelines in [26]. We have defined a protocol, verified it, and started conducting the review. We considered it useful to involve graduate students in the data extraction phase of the process since they were familiar to SPC, because it is part of their curricula. We consider the training that students were given on systematic review complete and satisfactory because it was based on an international school on empirical software engineering, and because feedback was positive.

Abstract Background: The XmR chart is a powerful analytical tool in statistical process control (SPC) for detecting special causes of variation in a measure of quality. In this analysis a statistic called the average moving range is used as a measure of dispersion of the data. This approach is correct for data with natural underlying order, such as time series data. There is however conflict in the literature over the appropriateness of the XmR chart to analyse data without an inherent ordering.

¹M.E. Scholar, Industrial Engineering, ²Associate Professor, Mechanical Engineering Department, 1, 2 G. H. Patel College of Engineering& Technology, Vallabh Vidyanagar, Anand, Gujarat Abstract - Excessive variability in process performance often results in waste and rework. For improvement in quality and productivity process variation needs to be reduced. For this Statistical Process Control techniques are used. SPC uses statistics to detect variations in the process so that it can be controlled. Control charts are used in SPC for measuring the variation in the process and that can be continuously improved by the different techniques used in the SPC such as 7 QC tools. This paper shows applicability of the statistical process control techniques in different manufacturing industries. In this research paper various research articles and the case studies on the implementation of the Statistical Process Control Techniques in the manufacturing industries are selected for the review.

Many problems of software process monitoring are hampering the quality of our software products. In this paper, we plan to address the problem of process instability and causes of process anomalies. These problems can be addressed using one of the powerful statistical techniques known as statistical process control (SPC). Also, control chart would be used in our study as it has been proved to be one of the suitable tools of SPC in monitoring process stability. As we know, the more defects we found during SDP, the less quality of the software product. Therefore, this study considers defect density as the metric to be use due to its significance in determining product quality.

Optimum Control Limits for Employing Statistical Process Control in Software Process Pankaj Jalote, Senior Member, IEEE, and Ashish Saxena Abstract—There is an increased interest in using control charts for monitoring and improving software processes, particularly quality control processes like reviews and testing. In a control chart, control limits are established for some attributes and, if any point falls outside the limits, it is assumed to be due to some special causes that need to be identified and eliminated. If the control limits are too tight, they may raise too many “false alarms” and, if they are too wide, they may miss some special situations. Optimal control limits will try to minimize the cost of these errors. In this paper, we develop a cost model for employing control charts to software process using which optimum control limits can be determined. Our applications of the model suggest that, for quality control processes like the inspection process, the optimum control limits may be tighter than what is commonly used in manufacturing. We have also implemented this model as a web-service that can be used for determining optimum control limits.

Lane et al. 133 proposed an extension to PCA which enables the simultaneous monitoring of a number of product grades or recipes. Schippers 134 proposed an integrated process control model using statistical process control, total productivity management and automated process control. Kano et al. 135 proposed a novel statistical monitoring method which is based on PCA, called moving PCA, in order to improve process-monitoring performance. The aim of this method is to identify changes in the correlation structure. Chen and Liu 136 proposed on-line batch process monitoring using dynamic PCA and dynamic PLS models. Finally, Arteaga and Ferrer 137 dealt with the missing-data problem in the estimation of latent variables scores from an existing PCA model. Badcock et al. 138 proposed two alternative projection techniques that focus on the temporal structure of multivariate data. Ramaker et al. 139 , using simulation, studied the effect of the size of the training set and number of principal components on the false-alarm rate in statistical process monitoring.

Abstract The use of statistical process control has gained a major importance in the last years due to very good results that is provides and due the ease interpretation of the results, even by the people who are not specialists in the field. An essential quality, that differs the statistical process control to the other quality analysis statistical methods is that it examines the process in all stages, not only in the final stage. The increase of the competitiveness in all areas of industry made that the methods used in quality control to be more performant. No organization can maintain a high standard without a performant quality control. The pharmaceutical industry is one of the most important industries, holding an essential role in human’s health in particular and in welfare of the whole society in general. This application is meant to illustrate, by using some of statistical indices, control diagrams and capability process indices, how it is used the statistical process control in the pharmaceutical industry and highlights both advantages and disadvantages of using it.

Abstract—Statistical process control methods for monitoring processes with individual measurements are considered and two new individual control charts for monitoring process variability and correlation are proposed. The influence function of variance is proposed to monitor process variability. To investigate correlation among two quality characteristics control charts based on the influence function of correlation coefficient are suggested. The advantage of our variance influential control chart is its ability to monitor process variance based only on the measurements of each inspected unit, which is not the case for classical moving range chart where differences from one point to the next are displayed in the graphic, so limiting its use in the matter of mated parts. The proposed techniques are general, and the influence functions may be used to build up individual control charts relative to either nominal values or estimates. The method is further illustrated with real datasets, from a manufacturing system producing precisely interfitting and mating parts.