Statistical Quality Study of the Parts Produced in an Automobile Industry: A Daimler India Case Study

Every manufacturing industry considers defect-free production in this competitive era. Though it is practically impossible to improve the rate of defect minimization, statistical tools can be used. In this case study, we take data from Daimler India, an automobile part manufacturing industry specialized in manufacturing OEM tools like chassis, oil filter nipple, and so on, and study how many defects are made during the day. The defect-causing process was eliminated after using statistical quality control tools such as np charts and cumulative sum charts, resulting in higher production quality.

Sea level acceleration under the magnifier

Detection and quantification of sea level accelerations at tide gauge stations are needed for assessing anthropogenic contributions to the climate change. Nonetheless, uniform or non-uniform sea level accelerations/decelerations are particularly di˚cult to discern partly because of their small magnitudes and partly because of the low frequency sea level variations as confounders. Moreover, noisy excursions in the observed sea level variations also exacerbate reliability of estimated sea level accelerations. This study explores the uniformity of a sea level acceleration graphically that is left unmodeled in the residuals of a least squares solution using cumulative sum charts. Key West, USA tide gauge station’s record is studied for a demonstration. The cumulative sum charts of the residuals of a rigorous kinematic model solution without the acceleration parameter revealed its crisp and uniform signature experienced at this station since 1913.

Features, Opportunities and Application of Control Cards Accumulated Sum. Part 2. Numerical Method for Assessing the Disorder of a Technological Process

The article continues to consider the possibility of maintaining the technological process in a statistical control state with the use of cumulative sum charts. A numerical method for estimating the statistical controllability of a process using a scheme of decision intervals based on a computational algorithm is considered. Cumulative sum charts can provide an out-of-control process detection and, unlike a regular Shewhart charts, allow determine quickly and accurately the process change area, as well as when corrective action is required. Unlike the graphical method using the V-mask, when the mandatory presence of an operator is required to monitor the state of the process, the numerical estimation method using the decision interval scheme can be automated and provide appropriate signals without operator involvement. The method under consideration reveals a point in time when a change in process cannot be caused solely by the influence of random causes, that is, there is a significant systematic influence, a disorder of the process and a shift in the primary level of adjustment. The use of the same V-mask allows to solve the opposite problem: when fixing the moment of disorder of the technological process to determine what time this event took place. When constructing a V-mask, its «opening angle» is directly related to the maximum permissible displacement of the process and, based on the requirements for the quality of the technological pro­cess, it is necessary to have an aggregate (set) of such V-masks. When applying the numerical method, this problem does not occur. The article shows the equivalence of graphical and numerical methods theoretically and numerically, which, given the certain undoubted advantages of the latter, proves the prospect of its application.

Book Reviews

Fitting Linear Relationships: A History of the Calculus of Observations 1750-1900.(R.W. Farebrother)Basic Business Statistic. (D.P. Foster, R.A. Stine, R.P. Waterman)Statistische und numerische Methoden der Datenanalyse. (V. Blobel, E. Lohrmann)The Practice of Time Series Analysis. (H. Akaike, G. Kitagawa)Finanzmathematik. Die Bewertung von Derivaten (A. Irle)Programming with Data. A Guide to the S Language (J.M. Chambers)Random Number Generation and Monte Carlo Methods. (J.E. Gentle)Wirtschafts- und Sozialwissenschaftliche Panel-Studien, Daten-Strukturen und Analyse-Verfahren. (R. Hujer, U. Rendtel, G. Wagner)Cumulative Sum Charts and Charting for Quality Improvement. (D.M. Hawkins,D.H. Olwell)Statistical Quality Control. Strategies and Tools for Continual Improvement. (J.Ledolter, C.W. Burrill)