Papers by Keyword: Statistical Process Control (SPC)

Abstract: Traditional control charts often struggle to simultaneously detect both small and large shifts in process parameters. This study proposes the AEWMA-Max method, an improved variant of the Adaptive Exponentially Weighted Moving Average Max (AEWMAM) chart, to address this challenge in the context of monitoring temperature fluctuations in vannamei shrimp ponds. The research employs a data set containing 26 out-of-control and 64 in-control temperature measurements. AEWMA-Max utilizes a dynamically adjusted smoothing parameter (L) to achieve optimum sensitivity for both subtle and significant deviations from the desired temperature range. Through extensive simulations and comparisons with existing control charts, L = 2.642 was identified as the most effective value for this specific application. The amount of out-of-control data on the control chart is the better metric for determining the best charts used in monitoring the process. Based on the monitoring results, the proposed AEWMA-Max method demonstrably outperforms traditional charts in detecting both small and large temperature shifts, offering enhanced process control and potentially improved shrimp survival rates.

Abstract: Recent literature shows that most safety-related standards are not yet finalized as long as they seem far from assessing a sought level of safety. In addition, the shortened and hasty assessment of the industrial safety depends solely on what directly endangers mankind security and its economic assets. Moreover, well-known quality standards have not yet established a well-defined code to formulate the safety and liability area of the product quality. Owing to the safety-related weak points mentioned above, the present paper puts forth a unified and applicable mathematical model. Moreover, this paper confirms that humanity's engineering willingness of a prospective industrial product (vehicle) along with its manufacturing plants has not to overlook crucial safety instructions for a multi-entity Environmental Closed System (ECS). The suggested environment-related approach is here checked using three commonly applied methods, namely, SPC, FMEA, and Markov Chains of industrial safety estimation for products /plants. Main findings of the present paper conclude that industrial (product/ plant) safety, in its broadened sense, does embrace the gain/loss statistical data of a product's introductory versions and represents a trade–off function of its profits (resource renovation) and its losses (resources drain). In addition, the comprehensive resource-loss trend helps product designers and concerned researchers meet a wide range of customer requirements and more operational regulations.

Abstract: 3D optical metrology methods are increasingly used in the research of sheet metal materials and in sheet metal production processes. Optical measuring systems are implemented in different process stages, including design, sheet metal material research and component development, tool making and production as well as series accompanying quality control.Today’s development processes are initially driven from computational methods. Especially for the development of sheet metal components the numerical forming simulation is an important tool. However, performing a reliable forming simulation requires accurate input parameters like 3D geometry data for meshing, material parameters and boundary conditions which can be obtained with optical measuring systems. Further on the validation of these numerical simulations is supported with optical full-field sheet metal forming analysis.In the tool manufacturing phase 3D measurement data contributes in reducing the time frame for CNC machining processes, for the try-out phase, future tool reproduction as well as for repair and maintenance.With automated 3D measuring solutions series accompanying quality control is performed to determine tool wear and to shorten the response time if problems in the production occur.This paper is extending past work [1] and discusses today’s contribution of optical 3D measuring techniques in sheet metal component development and production, covering the areas of determining input parameters for sheet metal forming simulations and its validation, tool manufacturing, including the try-out, and production quality control using automated optical measurement machines.

Abstract: SPC method is a process controlling tool with the aid of mathematical method. Define, Measure, Analysis, Improvement and Control is the implementation processes of quality management. Combined with the two methods, the quality fluctuation in the production process could be controlled effectively and qualified products rate could be enhanced excellently. In this paper, the film thickness problem of motor shell coating production line has been studied based on statistical process control and DMAIC processes. The Pareto diagram, cause and effect diagram, operation chart are used to inspect production defects in the process. At same time, the factors leading to product defects are determined. Then, DOE method is applied to find the best parameters of electrophoresis coating process. SPC method is adopted to monitor the improved film thickness. The results show that quality level of coating process has improved greatly.

Abstract: Implementation of management by processes in Romania it is a problem if we consider its effects: improving performances of organizations expressed in terms of quality, process duration, cost, etc. Taking into account the sequence of steps corresponding to the specific managerial process and quality management, it is considered that its functions are: planning, organizing, coordinating, controlling, quality assurance and improvement. This paper presents a detailed approach of advanced product quality planning (APQP) of technological products and the case study regarding the analysis of industrial product defects implementing statistical process control (SPC). The Production Part Approval Process (PPAP) purpose continues to be to provide the evidence that the specification requirements are clearly understood by the organization and the manufacturing processes are the designed capability. Implementing the APQP technique permits us to define and establish the steps necessary to ensure that a product satisfies the customers requirements.

Abstract: Up to now, several methods have been proposed for monitoring processes with attribute data. These methods can be categorized into two major group; statistical methods and fuzzy methods. In this paper current fuzzy methods are introduced and the performance of fuzzy methods and statistical methods are compared together based on the Average Run Length (ARL). The comparison shows that the statistical method has the best performance. We show the necessity of using fuzzy method in case of attribute data. Then the critiques towards fuzzy methods are reviewed which show the usage of fuzzy set theory in these methods have some restriction. As a result we indicate a study gap about the usage of fuzzy set theory for monitoring processes with attribute data and at the end some guideline for the next study are proposed.

Abstract: A method of determining the optimal number of inspectors and/or working time required on a specific SPC activity is presented in the study. The issue of inspection manpower planning is handled as a constrained optimization problem. The optimization strategy is not only to minimize the avoidable surplus quality loss due to failure of detecting the out-of-control states but to determine the cost of inspection manpower from the perspective of deploying an appropriate amount of inspection manpower in a cost-effective manner, and meanwhile the values of sample size, sampling interval and control limits of control charts are also determined. The result obtained indicates that the total cost (or loss) can be substantially reduced if implementing control charts was equipped with adequate inspection manpower.

Abstract: Complex Products may present more than one type of defects and these defects are not always of equal severity. These defects are classified according to their seriousness and effect on product quality and performance. Demerit systems are very effective systems to monitoring the different types of defects. So, classical demerit control chart used to monitor counts of several different types of defects simultaneously in complex products. Recently, H.W. Kang et al.[7] introduced Demerit-GWMA(generally weighted moving average) and Demerit-EWMA control charts that can detect small shifts of the process mean more sensitively than the classical demerit control charts. In this paper, we present an effective method for process control using the Demerit-GWMA statistics with fast initial response. Moreover, we evaluate exact performance of the Demerit-GWMA control chart with fast initial response(FIR), Demerit-GWMA and Demerit-EWMA according to changing sample size or parameters.

Abstract: A real-time WPNN-based model was present for the simultaneous recognition of both mean and variance CCPs. In the modeling of structure for patterns recognition, the combined wavelet transform with probabilistic neural network (WPNN) was proposed. Input data was decomposed by wavelet transform into several detail coefficients and approximations. The approximation obtained and energy of every lever detail coefficients was for the input of PNN. The simulation results shows that it can recognize each pattern of the mean and variance CCPs accurately, which can be used in simultaneous process mean and variance monitoring.

Abstract: For the high and strict quality requirement in the manufacturing process of nuclear power parts, this paper is based on the combination of Statistical Process Control technology and the ERP quality management and control the production quality based on the control chart. PowerBuilder 9.0 and SQL Server2000 were used to design and develop the system while PowerBuilder 9.0 as front-end development tool and SQL Server2000 as back-end DBMS respectively. Firstly, collect the quality data of the production process (some important processes). Then, analysis these data and form control chart. Real-time monitor production process by the control charting to ensure the process is stability. Organic combination of SPC and ERP to improve and control the quality, not only enrich the analytical data of SPC, but also make up the ERP data to analysis and control quality data.