Multiresponse optimization of a multistage manufacturing process using a patient rule induction method

Most manufacturing industries produce products through a series of sequential stages, known as a multistage process. In a multistage process, each stage affects the stage that follows, and the process often has multiple response variables. In this paper, we suggest a new procedure for optimizing a multistage process with multiple response variables. Our method searches for an optimal setting of input variables directly from operational data according to a patient rule induction method (PRIM) to maximize a desirability function, to which multiple response variables are converted. The proposed method is explained by a step-by-step procedure using a steel manufacturing process as an example. The results of the steel manufacturing process optimization show that the proposed method finds the optimal settings of input variables and outperforms the other PRIM-based methods.     

Improving the Product Reliability in Multistage Manufacturing and Service Operations

Monitoring and improving the product reliability is of main concern in a large number of multistage manufacturing processes. The process output is commonly inspected under limited load conditions, and the tensile strength of reliability‐related quality characteristic is measured. This brings about censored observations that make the direct application of traditional control charts futile. The monitoring procedure becomes aggravated when the influence of variable competing risk is pronounced during the conducted test. To deal with this critical issue, we propose a regression‐adjusted cumulative sum (CUSUM) chart to effectively monitor a quality characteristic that may be right censored because of both fixed and variable competing risks. Moreover, two exponentially weighted moving average (EWMA) control charts on the basis of conditional expected values are devised to detect decreases in the tensile mean. The comparison of the three competing monitoring schemes confirms the superiority of the regression‐adjusted CUSUM procedure. Not only is the proposed control chart applicable to manufacturing processes with the aim of monitoring reliability‐related quality variables, it is also appropriate for monitoring similar quality measurements in service operations such as survivability measures in healthcare services. Copyright © 2011 John Wiley & Sons, Ltd.     

Reliability and fault-tolerance in multistage interconnection networks

Reliability and fault-tolerance issues are important in the study of interconnection networks used in large multiprocessor systems because of the large number of components involved. In this paper we study these issues with respect to multistage networks which are typically built forN inputs andN outputs using 2 × 2 switching elements and log₂ N stages. In such networks, the failure of a switching element or connecting link destroys the communication capability between one or more pair(s) of source and destination terminals. Many techniques exist for designing multistage networks that tolerate switch and/or link failures without losing connectivity. Several approaches for achieving fault-tolerance in multistage interconnection networks are described in this paper. The techniques vary from providing redundant components in the network to making multiple passes through the faulty network. Quantitative measures are introduced for analysis of the reliability of these networks in terms of the component reliabilities. Several examples are given to illustrate the techniques. This research is supported by thensf Presidential Young Investigator Award No.dci-8452003, a grant from AT&T Information Systems, and a grant fromtrw.     

Strategies for planning experiments using orthogonal arrays and confounding tables

Genichi Taguchi has popularized a robust design method which employs experimental design techniques to help identify the levels of design factors to improve the quality of products and manufacturing processes. Experimental design techniques are extremely effective for identifying improved factor levels in problems that involve a large number of factors. Taguchi's success in getting engineers to use experimental design techniques is due, at least in large part, to his use of tools and techniques that simplify the experiment planning process. Recognizing the advantages of this approach, this paper proposes a new set of tools, confounding tables, which offer more guidance to experimenters. Confounding tables provide a clear and systematic representation of confounding relationships. They are simple and useful tools for constructing experiment plans, and they enable users easily to evaluate the confounding patterns of a completed plan. We show how confounding tables provide more information than Taguchi's linear graphs, and are useful for a large class of experiment plans.     

Economic batch quantity in a multi-stage production system

A mathematical model has been developed in this paper for determining the total annual variable cost for a product which requires processing on a number of production stages. The demand for the product is assumed uniform over time and it is manufactured in equal lot sizes. In order to minimize the manufacturing cycle time of o production lot, the movement of the items between production stages is in sub-batches of equal sizes, As a result of manufacturing a production lot in sub-batches, the following additional costs are incurred: (1) additional cost of stock holding for process inventory; (2) cost of transporting sub-batches; (3) cost of multiple set-ups. A simple method is then adopted for minimizing the total annual variable cost of the multistage production system. An example has been solved to illustrate the method.     

Optimum machine selection in multistage manufacturing systems

Machine selection during the initial stages of facility planning is critical as most capital costs are incurred in the investment of new machines. This paper presents an approach for optimizing the number of machines acquired for batch processing in a multistage manufacturing system. Machines of the same type differ in their processing capabilities. Four cases of overlap in machine capabilities are examined. For each case, the problem is optimized with and without the time balance constraints between the stages. The output is the optimum number of machines of each type to be purchased for each stage, as well as the optimum time delay between the stages such that the system cost is minimized. The resulting multistage line is then simulated under specified conditions to observe its behaviour over time and to assess the viability of the developed model.     

Multistage PRIM: patient rule induction method for optimisation of a multistage manufacturing process

Industries such as automotive, LCD, PDP, semiconductor and steel produce products through multistage manufacturing processes. In a multistage manufacturing process, performances of stages are not independent. Therefore, the relationship between stages should be considered when optimising the multistage manufacturing process. This study proposes a new procedure of optimising a multistage manufacturing process, called multistage PRIM (patient rule induction method). Multistage PRIM extends the scope of process optimisation from a single stage to the multistage process, and it can use the information encapsulated in the relationship between stages when maximising each stage's performance. A case study in a multistage steel manufacturing process is conducted to illustrate the proposed procedure.     

A decision support system for selection of net-shape primary manufacturing processes

Developments in the capabilities of the manufacturing processes increased the number of processes that can produce a part within the requirements determined by its design and market research. The increased number of processes and unfamiliarity of manufacturing engineers to many new manufacturing processes forces the researchers to develop systematic process selection tools instead of depending on the accumulated human expertise only. In this paper, a net-shape primary manufacturing process selection decision support system (DSS), which is named PROSEL (PROcess SELection), is developed. The developed selection programme eliminates the unsuitable processes step by step by checking a part’s material, annual production quantity, specified shape, thickness and presents the most economical process as the most appropriate net-shape primary process after a final cost analysis. The developed DSS is written in Visual Studio and tested with a great deal of real-life examples. It can be concluded from the tests that the programme provides the same or better primary manufacturing process selection decisions than the practical usage, and it is a very useful support tool for net-shape primary process selections.     

An alternative approach to test process capability for unilateral specification with subsamples

Process capability indices are useful management tools, which provide common quantitative measures on manufacturing capability and production quality. The indices C_PU and C_PL are designed specifically for processes with one-sided manufacturing specifications. The majority of the results obtained so far related to the distributional properties of the estimated capability indices were derived based on the assumption of possessing a single sample. However, a common practice in process control is to estimate the process capability indices by using the past ‘in control’ data from several subsamples. In order to use previous in-control data from multiple subsamples to make correct decisions regarding process capability, the distribution of the estimated capability index based on multiple subsamples should be available. In this paper, we develop a capability testing procedure with one-sided specifications using a Bayesian approach based on subsamples collected over time from an in-control process. By applying the proposed testing procedure, the practitioners can make reliable decisions to determine whether their processes meet the pre-set capability requirement when a daily based or weekly based production control plan is implemented for monitoring process stability.     

Performance evaluation of two-stage multi-product kanban systems

We propose an approximate evaluation procedure for a kanban-controlled production system with two stages and multiple products. In the first stage, single-product manufacturing facilities produce items that are the input material for a single multi-product manufacturing facility in the second stage. Each manufacturing facility is controlled by a distinct kanban loop with a fixed number of kanbans. Processing and setup times are exponentially distributed, demand arrivals at the output store of the second stage are Poisson and independent for each product. If a customer's demand cannot be met from stock, the customer either waits or leaves the system, depending on the admissible number of backorders and the current number of waiting customers (partial backordering). We describe a new decomposition-based approximation method for the evaluation of such systems in steady state. We focus on the performance measures average fill rate, average fraction of served demand, and average inventory level. We report the results of several numerical tests. The results indicate that the approximation is sufficiently accurate for a large variety of systems. We also illustrate the effects of increasing the maximum number of backorders on the performance of the system.     

Robot selection using a fuzzy regression-based decision-making approach

Industrial robots, which enable manufacturing firms to produce high-quality products in a cost-effective manner, are important components of advanced manufacturing technologies. The performance of industrial robots is determined by multiple and conflicting criteria that have to be simultaneously considered in a robust selection study. In this study, a decision model based on fuzzy linear regression is presented for industrial robot selection. Fuzzy linear regression provides an alternative approach to statistical regression for modelling situations where the relationships are vague or the data set cannot satisfy the assumptions of statistical regression. The results obtained by employing fuzzy linear regression are compared with those of earlier studies applying different analytical methods to a previously reported robot selection problem.     

Polling systems with a patient server and state-dependent setup times

We analyze a class of cyclic service (polling) systems with multiple customer classes (stations) in which the server stops cycling upon finding the entire system empty and initiates a setup only when the polled station has at least one customer in the queue. Interest in such systems is fueled by applications in design and performance analysis of manufacturing as well as telecommunication systems, We develop a discrete Fourier transform (DFT)-based near-exact numerical technique and an approximate method for systems with any number of stations. The DFT-based algorithm is accurate but computationally demanding when either the number of stations is large or server utilization is high. In these cases, the approximate method appears to work well in a large number of numerical tests.     

Modelling robustness in serial multi-stage manufacturing processes

The study of robustness in single-stage manufacturing has been explored by a large number of researchers and practitioners. However, modelling of robustness in multi-stage manufacturing using multivariate data is seldom used. The aim of this paper is to develop a methodology to model process robustness in a serial multi-stage manufacturing system. Combining statistical regression, Taylor series expansion, the root-sum-squares method and a variation model, the methodology proposes a measurement system for robustness. The resulting metric, while quantifying robustness, measures absorbed and transmitted variations across the stages of a manufacturing process. Using the methodology in a serial two-stage worm gear manufacturing process, the levels of robustness and both absorbed and transmitted variations are determined, thus identifying significant variations across manufacturing stages. The details of this application with the types of corrective actions as required for minimisation of process performance deterioration are presented.     

A smart manufacturing adoption framework for SMEs

Smart Manufacturing (SM) a revolutionary paradigm that aims to improve production systems’ performance in terms of quality, time, cost, and flexibility, as well as human and machine decision-making capabilities. Most large enterprises have already taken first steps towards adopting SM. Small and Medium-sized Enterprises (SMEs) on the other hand, are struggling with developing a SM adoption roadmap. Our research builds on the real and perceived needs and challenges faced by manufacturing SMEs and advances the field by developing and evaluating an SME-specific ‘SM adoption framework’. We have employed a multiple case study approach to acknowledge the lessons learned by selected early-adopter SMEs that have recently implemented and deployed SM tools and practices. We propose an SM adoption framework with five vital steps that SMEs interested in SM should follow: (i) identify manufacturing data available within the SME, (ii) readiness assessment of the SME data-hierarchy steps, (iii) developing SM awareness of SME leadership and staff, (iv) develop a SM tailored vision for the SMEs, and (v) identify appropriate SM tools and practices necessary to realise the tailored SM vision. Moreover, the results of the case study analysis enabled us to formulate many generalisations.     

An integrated decision support system for strategic supply chain optimisation in process industries: the case of a zinc company

We introduce a menu-driven user-friendly decision support system (DSS) for supply chain planning based on optimisation. The DSS is based on a multi-source (supplier), multi-destination (warehouse) network having multiple manufacturing facilities, with multiple materials and multiple storage areas. This integrated supply chain model performs multiple period planning. The use of this DSS requires little knowledge of management sciences tools. We discuss the need for an integrated approach towards supply chain modelling for the process industry. We present the integrated model in the form of a database structure. We validate the model with the real data of a zinc company and demonstrate the impact of optimisation in terms of percentage improvement. The result shows that it is possible to improve unit contribution to profit from 1.89 to 4.66%.     

Huffman encoding of test sets for sequential circuits

Sequential circuits are hard to test because they contain a large number of internal states that are difficult to control and observe. Scan design is often used to simplify testing; however, scan is not always applicable because of area and performance penalties. Recent advances in sequential circuit testing have led to techniques and tools that provide test sets with high coverage of single stuck-line (SSL) faults for nonscan circuits. However, these test sets contain a large number of patterns and require a tester with considerable pattern depth. We investigate the application of Huffman codes to pattern encoding. This allows the use of low-cost testers that do not require excessive memory. Our method is especially applicable to nonscan and partial-scan embedded core circuits. We demonstrate the feasibility of our approach by applying it to SSL test sets for the ISCAS'89 benchmarks     

A multi-model approach to determine early manufacturing parameters for small-data-set prediction

Constructing an accurate prediction model from a small training data set is an important but difficult task in the field of forecasting. This is because when the data size is small, the incomplete data may mean that the model produced cannot sufficiently represent the true data structure or cause the model training to be overfitted. To address this issue, this paper presents an approach that combines multiple prediction models to extract data information in multiple facets. In the multi-model approach, a compromise weight method is proposed to determine the relative reliability of each of the prediction model. The methods used include multiple regression, artificial neural network, and support vector machines for regression. A thin-film transistor liquid crystal display manufacturing case study is used to illustrate the details of this research. The empirical results not only show that the proposed multi-model can reduce the manufacturing variation and increase the production yield, but also can propose a robust and reliable parameter interval to the online engineers in the early manufacturing stage.     

Wire + Arc Additive Manufacturing

Depositing large components (>10?kg) in titanium, aluminium, steel and other metals is possible using Wire + Arc Additive Manufacturing. This technology adopts arc welding tools and wire as feedstock for additive manufacturing purposes. High deposition rates, low material and equipment costs, and good structural integrity make Wire+Arc Additive Manufacturing a suitable candidate for replacing the current method of manufacturing from solid billets or large forgings, especially with regards to low and medium complexity parts. A variety of components have been successfully manufactured with this process, including Ti–6Al–4V spars and landing gear assemblies, aluminium wing ribs, steel wind tunnel models and cones. Strategies on how to manage residual stress, improve mechanical properties and eliminate defects such as porosity are suggested. Finally, the benefits of non-destructive testing, online monitoring and in situ machining are discussed.     

An upper bound on the weight-balanced testing procedure with multiple testers

This paper presents the performance of the Weight-Balanced Testing (WBT) algorithm with multiple testers. The WBT algorithm aims to minimize the expected number of (round of) tests and has been proposed for coding, memory storage, search and testing applications. It often provides reasonable results if used with a single tester. Yet, the performance of the WBT algorithm with multiple testers and particularly its upper bound have not been previously analyzed, despite the large body of literature that exists on the WBT algorithm, and the recent papers that suggest its use in various testing applications. Here we demonstrate that WBT algorithm with multiple testers is far from being the optimal search procedure. The main result of this paper is the generalization of the upper bound on the expected number of tests previously obtained for a single-tester WBT algorithm. For this purpose, we first draw an analogy between the WBT algorithm and alphabetic codes; both being represented by the same Q-ary search tree. The upper bound is then obtained on the expected path length of a Q-ary tree, which is constructed by the WBT algorithm. Applications to the field of testing and some numerical examples are presented for illustrative purposes.