Search results

Control chart pattern recognition is a critical issue in statistical process control, as unnatural patterns on control charts are often associated with specific assignable causes adversely affecting the process. Several researchers have recently applied neural networks to pattern recognition for control charts. However, nearly all studies in this area assume that the in‐control process data in the control charts follow a normal distribution. This assumption contradicts the facts of practical manufacturing situations. This paper investigates how non‐normality affects the performance of neural network based control chart pattern recognition models. Extensive performance evaluation was carried out using simulated data with various non‐normalities. The non‐normality was measured in skewness and kurtosis. Numerical results indicate that the neural network based control chart pattern recognition models still perform well in a non‐normal distribution environment in terms of recognition accuracy and speed.

The purpose of this paper is to develop a control chart pattern recognition methodology for monitoring the weekly customer complaints of outsourced information technology-enabled service (ITeS) processes.

A two-step methodology is used to classify the processes as having natural or unnatural variation based on past 20 weeks' customer complaints. The step one is to simulate data on various control chart patterns namely natural variation, upward shift, upward trend, etc. Then a deep learning neural network model consisting of two dense layers is developed to classify the patterns as of natural or unnatural variation.

The validation of the methodology on telecom vertical processes has correctly detected unnatural variations in two terminated processes. The implementation of the methodology on banking and financial vertical processes has detected unnatural variation in one of the processes. This helped the company management to take remedial actions, renegotiate the deal and get it renewed for another period.

This study provides valuable information on controlling information technology-enabled processes using pattern recognition methodology. The methodology gives a lot of flexibility to managers to monitor multiple processes collectively and avoids the manual plotting and interpretation of control charts.

The application of control chart pattern recognition methodology for monitoring service industry processes are rare. This is an application of the methodology for controlling information technology-enabled processes. This study also demonstrates the usefulness of deep learning techniques for process control.

Statistical quality control charts cannot indicate explicitly whether there is any special disturbance in the manufacturing process. pattern recognition scheme can solve this problem. The simultaneous control of two or more variables is necessary when the quality of the product depends on the joint effect of these variables. Studies the combination patterns of random and random, shift and cycle, trend and cycle, and trend and shift for two variables. Proposes a T² control chart and uses simulation to determine pattern diagnostic characteristics for these combinations. The pattern diagnostic characteristics studied are window size, zone boundary, and zone representation. The results indicate that window size 20 is appropriate for these particular parameters, equal probability and the highest percentage alternative are adopted as the zone boundary and the zone representation, respectively. The sensitivity analysis of the pattern parameters indicates the pattern diagnostic is robust for changes in the parameter values.

Pattern recognition applied to control charts centers around the development and assessment of automated algorithms for detecting non‐random or unnatural patterns in observations collected from a production process. The work presented here marks the first examination of enhancements to an existing algorithm, of investigations into sensitivity analysis issues, of development of standard performance metrics, and of a comparative performance with the traditional Western Electric Run tests. The simulation results of the research presented here indicate that the modified algorithm performs markedly better than the original algorithm, is only slightly sensitive to the selection of the user specified algorithm parameters, and competes favorably with the Western Electric Run Tests especially when detecting repetitive patterns like cycles.

Quality control charts are statistical process control tools aimed at monitoring a (manufacturing) process to detect any deviations from normal operation and to aid in process diagnosis and correction. The information presented on the chart is a key to the successful implementation of a quality process correction system. Pattern recognition methodology has been pursued to identify unnatural behaviour on quality control charts. This approach provides the ability to utilize patterning information of the chart and to track back the root causes of process deviation, thus facilitating process diagnosis and maintenance. Presents analysis and development of a statistical pattern recognition system for the explicit identification of unnatural patterns on control charts. Develops a set of statistical pattern recognizers based on the likelihood ratio approach and on correlation analysis. Designs and implements a training algorithm to maximize the probability of identifying unnatural patterns, and presents a classification procedure for real‐time operation. Demonstrates the system performance using a set of newly defined measures, and obtained results based on extensive experiments illustrate the power and usefulness of the statistical approach for automating unnatural pattern detection on control charts.

Driven by the development in sensing techniques and information and communications technology, and their applications in the manufacturing system, data-driven quality control methods play an essential role in the quality improvement of assembly products. This paper aims to review the development of data-driven modeling methods for process monitoring and fault diagnosis in multi-station assembly systems. Furthermore, the authors discuss the applications of the methods proposed and present suggestions for future studies in data mining for quality control in product assembly.

This paper provides an outline of data-driven process monitoring and fault diagnosis methods for reduction in variation. The development of statistical process monitoring techniques and diagnosis methods, such as pattern matching, estimation-based analysis and artificial intelligence-based diagnostics, is introduced.

A classification structure for data-driven process control techniques and the limitations of their applications in multi-station assembly processes are discussed. From the perspective of the engineering requirements of real, dynamic, nonlinear and uncertain assembly systems, future trends in sensing system location, data mining and data fusion techniques for variation reduction are suggested.

This paper reveals the development of process monitoring and fault diagnosis techniques, and their applications in variation reduction in multi-station assembly.

Prototype patterns and pattern diagnostic characteristics have been proposed in a previous article. Simulation results based on the prototypes and the diagnostic characteristics have also been presented as a justification for the study. Outlines a methodology, with three major components, which designates eight processors to identify the unnatural pattern. The working memory (blackboard) characterizes the symbolic structure of the transformed data and stores the intermediate results from each processor. Eight processors are the kernel of the knowledge base used to classify the pattern of the observations. The comparison of intermediate results is executed in the inference engine, which makes the preliminary decision. The implementation of the processors is coded in Turbo C and runs on an IBM PC/XT/AT or compatible PC. The results of the implementation and validation demonstrate that the methodology does a good job for two‐variable pattern recognition.

The statistical process control chart is a monitoring technique useful in determining whether a process is behaving as intended or if there are some unnatural causes of variation. A process is considered to be out of control if a point falls outside the control limits or a series of points exhibit an unnatural pattern (also known as nonrandom variation). Analysis of unnatural patterns is an important aspect of control charting. It is well known that a particular unnatural pattern on a control chart is often associated with a specific set of assignable causes. Identification of unnatural patterns can greatly narrow the set of possible causes that must be investigated, hence facilitating the rapid diagnosis and corrective action.

Process monitoring is a way to manage the quality characteristics of products in manufacturing processes. Several process monitoring based on machine learning algorithms have been proposed in the literature and have gained the attention of many researchers. In this paper, the authors developed machine learning-based control charts for monitoring fraction non-conforming products in smart manufacturing. This study proposed a relevance vector machine using Bayesian sparse kernel optimized by differential evolution algorithm for efficient monitoring in manufacturing.

A new approach was carried out about data analysis, modelling and monitoring in the manufacturing industry. This study developed a relevance vector machine using Bayesian sparse kernel technique to improve the support vector machine used to both regression and classification problems. The authors compared the performance of proposed relevance vector machine with other machine learning algorithms, such as support vector machine, artificial neural network and beta regression model. The proposed approach was evaluated by different shift scenarios of average run length using Monte Carlo simulation.

The authors analyse a real case study in a manufacturing company, based on best machine learning algorithms. The results indicate that proposed relevance vector machine-based process monitoring are excellent quality tools for monitoring defective products in manufacturing process. A comparative analysis with four machine learning models is used to evaluate the performance of the proposed approach. The relevance vector machine has slightly better performance than support vector machine, artificial neural network and beta models.

This research is different from the others by providing approaches for monitoring defective products. Machine learning-based control charts are used to monitor product failures in smart manufacturing process. Besides, the key contribution of this study is to develop different models for fault detection and to identify any change point in the manufacturing process. Moreover, the authors’ research indicates that machine learning models are adequate tools for the modelling and monitoring of the fraction non-conforming product in the industrial process.