Quality Loss Function Research Articles

Impact of integrative design on additive manufacturing quality

To move additive manufacturing (AM) into a realm of credible manufacturing, quality evaluation techniques must be established to highlight the potential gains of AM technologies in the field of production quality in terms of dimensional control. This research aims to express the relationship among AM-enabled integrative design and quality evaluation techniques. The methodology proposed is backed by a comprehensive literature review that covers AM dimensional quality and conventional quality assessment techniques for production. The research proposes modelling the positive impact of integrating design using Taguchi’s quality loss function (QLF) and tolerance stack-up models. In addition, the research provides a straightforward way to evaluate AM-enabled integrated designs that promotes the proliferation of AM technology as a sustainable and credible manufacturing method. A case study is presented that describes how to apply Taguchi’s QLF to AM integrated designs.

Joint determination of optimum process mean, production run length and specification limits for a deteriorating process

Most of the recent work found in literature solved the problem of determining the optimum values of process parameters by considering one or jointly two parameters using separate models under different assumptions. The objective of this work is to develop a trine model that can be used for joint determination of three process parameters, namely: optimum process mean, production run length and specification limits, under mixed quality loss function for processes that are subject to deterioration over time. This paper will summarise the recent related literature and outlining the technical information required for this work. In this work, the problem will be tracked in two ways: by minimising the total loss and by maximising the net profit. For achieving that, we developed different models that can be used to determine optimum values for process parameters; the analysis leads to the development of the trine model. Numerical examples parallel to each model are presented to illustrate its use in determining the desired optimum parameter value. Sensitivity analysis for different process parameters are also presented to study their effects on the net profit in the view of satisfying the manufacturing requirements.

Bionic Fan Optimization Based on Taguchi Method

In this research, the multi-response optimization of mass flow rate and A-weighted SPL using Taguchi quality loss function has been done for bionic fan performance. The factors of the geometric parameters selected in this investigation are blade number, boss ratio, and blade stagger angle. The contribution of each parameter factor to the performance of bionic fan has been determined. The blade stagger angle has been found as the most effective factor and its contribution is 52.58% on multiple quality characteristics. The verification test has also been performed based on the optimum conditions predicted. The values of the mass flow rate and the A-weighted SPL at the optimum levels of the fan parameters are 0.4518 kg/s and 61.47 dB(A), respectively against the initial fan of 0.3438 kg/s and 70.50 dB(A). The mass flow rate and the A-weighted SPL have been increased by 0.1080 kg/s and decreased by 9.03 dB(A), respectively. The optimization results demonstrate considerable improvement in both mass flow rate and A-weighted SPL with the multiple response optimization combination, as compared with those of the initial fan.

The optimum settings for order quantity, process quality level, and warranty period

Chen and Liu’s (2007) [19] model presented the optimum profit model between the supplier and the buyer for the supply chain system. However, their model with simple manufacturing cost did not consider the used cost of customers in pure procurement policy. In this study, the authors propose a modified Chen and Liu’s (2007) [19] model for obtaining the optimum order quantity, process quality level, and warranty period of product by maximizing the expected total profit of the society. The advantage of this modified model is to obtain the joint control of inventory and quality control. Taguchi’s quadratic quality loss function will be applied in evaluating the product quality. Finally, sensitivity analysis of parameters will be provided for illustration.

Optimum profit model based on order quantity, product price, and process quality level

The maximum expected profit model between the producers and the purchasers is an important objective for the supply chain system. The producer’s profit needs to consider the problem of sales revenue and manufacturing cost. The purchaser’s profit needs to consider the problem of order quantity and used cost of customer. How to get a trade-off between them should be an important topic.Chen and Liu (2007) presented the optimum profit model between the producers and the purchasers for the supply chain system with pure procurement policy. However, their model with simple manufacturing cost did not consider the used cost of customer. In this study, the modified Chen and Liu’s model will be addressed for determining the optimum product and process parameters. The authors propose a modified Chen and Liu’s model with indirectly measurable quality characteristic under the single stage screening procedure. The surrogate variable with high correlation with indirectly measurable quality characteristic will be directly measured. The used cost of customer can be obtained by adopting Taguchi’s quadratic quality loss function. The optimum purchaser’s order quantity, the producer’s product price, and the process quality level will be jointly determined by maximizing the expected profit between them.

A Study of Selective Assembly for Product with Multi Mating Features

In order to firstly assure the mating features of high importance during the selective assembly process, a selective assembly method considering the feature weightings is proposed. All of the features are evaluated by fuzzy entropy weight method. Their weight coefficients which present the importance are defined. Based on the dissymmetrical quality loss function and the weight coefficients, the multi-objective model for selective assembly is established. A specific generic algorithm considering target weightings is used to solve the optimization model. It can search the preference region using the Pareto dominant order to derive satisfactory solutions with high quality. Finally, the method is used for the selective assembly of a certain aero engine’s subassembly to invalidate the feasibility.

Optimization of Multi-Response Problems Using Taguchi's Quality Loss Function Based on Grey Relational Grade

This article presents an approach which first combines grey relational grade and weighted quality loss function to convert the values of multiple responses obtained from each of the Taguchi orthogonal designed experiments into a single performance evaluation value. Then the analysis of variance (ANOVA) and the SN ratio based Taguchi analysis are conducted to find out respectively the relative importance of the process parameters and a set of near optimal parameter settings. A validation experiment is then conducted to confirm the finding. A case of multi-response turning process optimization is used to illustrate the proposed approach. Two sets of weights for the total quality loss were applied and the results were compared. The effectiveness of this approach was demonstrated by the improvement of turning performance in the both weight settings.

Multi-response design of Nd:YAG laser drilling of Ni-based superalloy sheets using Taguchi’s quality loss function, multivariate statistical methods and artificial intelligence

This paper presents a hybrid design strategy for the determination of the optimum laser drilling parameters which simultaneously meets the requirements for seven quality characteristics (responses) of the holes produced during pulsed Nd:YAG laser drilling of a thin sheet of nickel-based superalloy Nimonic 263. The process was designed using two approaches based on the experimental data. In the first approach, the quality losses of seven correlated responses were uncorrelated into a set of components using the principal component analysis; then the grey relational analysis was applied to synthesise components into a synthetic performance measure. Since this approach considered only parameter values used in the experiment, the second approach was developed to find the global optimal parameters solution using an artificial neural network to model the relation between parameters and a synthetic performance measure, and a genetic algorithm to perform a search for the global optimum in a continual multidimensional space. The analysis of the application indicated that the proposed approaches gave a better result, in terms of the optimal parameter settings that yield the maximal synthetic performance measure, than several commonly used methods for multi-response process parameters design. The results demonstrated that the robust Nd:YAG laser drilling of Ni-based superalloy sheets was designed with respect to the requirements for seven quality characteristics of the drilled holes, by using the proposed strategy.

Integrated total cost and Tolerance Optimization with Genetic Algorith

The tolerance allocation problem has been studied in the literature for decades, usually using mathematical programming (or) heuristic optimization approaches. Elegant tools for minimum cost tolerance allocation have been developed over several decades but still there is no specified tool to find the total cost with respect to machining cost and asymmetric quality loss functions. Objective of this paper is to find the optimized total cost by considering the machining cost and the asymmetric quality loss of an assembly. The non linear multi variable optimization of total cost problem formulated is solved using genetic algorithm. In this work, Piston and cylinder arrangement example was considered for concurrent allocation of design and machining tolerance, as well as to optimize the total cost. The result shows, optimized tolerance will enhances the quality and reduces the total cost

Multi-response optimization of oil agglomeration with multiple performance characteristics

In this paper, the multi-response optimization of grade and recovery simultaneously using Taguchi quality loss function has been done for Zonguldak/Turkey bituminous coal by oil agglomeration. The controllable factors selected in this investigation are solid content, amount of oil, agitation time and agitation rate. The percentage contribution of each controllable factor has been determined on the performance of oil agglomeration. The amount of oil has been found as the most effective factor and its contribution is 65.42% on multiple quality characteristics. The confirmation experiment has also been carried out according to the optimum conditions predicted. The grade and recovery have been increased up to 0.565% and 93.04%, respectively against the initial value of grade and recovery as 0.436% and 75.08%, respectively. The results show considerable improvement in both the quality characteristics such as grade and recovery with the multi-response optimization used, as compared the initial value of grade and recovery.

Concurrent optimization of machining process parameters and tolerance allocation

With the advent use of sophisticated and high-cost machines coupled with higher labor costs, concurrent optimization of machining process parameters and tolerance allocation plays a vital role in producing the parts economically. In this paper, an effort is made to concurrently optimize the manufacturing cost of piston and cylinder components by optimizing the operating parameters of the machining processes. Design of experiments (DoE) is adopted to investigate systematically the machining process parameters that influence product quality. In addition, tolerance plays a vital role in assembly of parts in manufacturing industries. For the selected piston and cylinder component, improvements efforts are made to reduce the total manufacturing cost of the components. By making use of central composite rotatable design method, a module of DoE, a mathematical model is developed for predicting the standard deviation of the tolerance achieved by grinding process. This mathematical model, which gives 93.3% accuracy, is used to calculate the quality loss cost. The intent of concurrent optimization problem is to minimize total manufacturing cost and quality loss function. Genetic algorithm is followed for optimizing the parameters. The results prove that there is a considerable reduction in manufacturing cost without violating the required tolerance, cutting force, and power.

A note on some modified Pulak and Al-Sultan's model

Pulak and Al-Sultan presented a rectifying inspection plan applying in the determination of optimum process mean. However, they did not point out whether the non-conforming items in the sample of accepted lot are replaced or eliminated from the lot and neglected the quality loss within specification limits. In this paper, we further propose the modified Pulak and Al-Sultan model with quadratic quality loss function. There are four cases considered in the modified model: (1) the non-conforming items in the sample of accepted lot are neither replaced nor eliminated from the lot; (2) the non-conforming items in the sample of accepted lot are not replaced but are eliminated from the lot; (3) the non-conforming items in the sample of accepted lot are replaced by conforming ones; (4) the non-conforming items in the sample of accepted lot are replaced by non-inspected items. The numerical results and sensitivity analysis of parameters show that their solutions are slightly different.

Design and manufacturing tolerances optimisation with quality loss functions

The competition in the current world market has forced the manufacturers to produce products with low cost and high quality. Production of high quality products at low cost requires the concurrent optimisation of design and manufacturing tolerances along with quality loss. Tolerance allocation is a design tool for minimising over-all cost of manufacturing, while meeting target levels for quality. Since, in traditional method, the allocation of tolerances is based on designer's own experience, it may significantly affect a product's quality and the resulting manufacturing costs. Hence, in this work, the tolerance allocation problem is formulated as a non-linear integer model by considering both the design and manufacturing tolerances so as to minimise the manufacturing cost and quality loss. Genetic algorithm is employed to solve the model and an example is presented to illustrate the methodology. Results are compared with conventional techniques and the performances are analysed.

Technical note: allocation of optimal tolerances in a mechanical assembly using DE and NSGA-II

This paper discusses a general methodology based on evolutionary algorithms (Elitist Non-dominated Sorting Genetic Algorithm (NSGA-II) and Differential Evolution (DE)) for allocation of optimal tolerance for an over-running clutch assembly. New hybrid models are developed for obtaining the manufacturing costs of hub, rollers and cage. The aim of this paper is to find optimal tolerances values that give minimum combined objective function value, minimum Manufacturing Cost (MC), minimum Quality Loss (QL) function and maximum Number of Standard Deviations (ZNSD) by satisfying stack-up conditions using non-traditional optimisation techniques. The results obtained from various techniques are compared and analysed.

The Application of Quality Loss Function to Acceptance Sampling(Recent Theories and Applications of Reliability and Safety)

The Application of Quality Loss Function to Acceptance Sampling(Recent Theories and Applications of Reliability and Safety)

A performance matrix for strategies to improve satisfaction among faculty members in higher education

Most studies of higher education focus on students as ‘customers’, and these studies tend to evaluate educational services on the basis of the satisfaction of these customers. This approach often neglects the question of the satisfaction (or dissatisfaction) of faculty members. The study designs a questionnaire for higher-education faculty members on the basis of the literature on this subject and discussion with scholars. Surveys of importance and satisfaction are then undertaken among Taiwanese faculty members with respect to various items. Each item is then placed on was modified a performance control matrix to determine an appropriate improvement strategy. Items that are found to be outside the range of an appropriate performance zone (APZ) are identified as objectives for improvement. The quality loss function (QLF) is then adopted to calculate an area of improvement objectives. A large QLF value indicates that faculty members satisfaction needs to be improved in these items. The results of this investigation demonstrate that retirement arrangements, job security, salaries, and fair promotion systems need to be improved. The resources of higher-education institutions must be invested appropriately to avoid waste and to enhance satisfaction among faculty members.

Application of genetic algorithm and Taguchi method in dynamic robust parameter design for unknown problems

Taguchi method was known in many industries as an off-line quality control methodology to improve the performance of products or processes at low cost. Although it was effective at improving quality, the statisticians pointed to inefficiencies in the method for highly nonlinear problems and complexity of the product design, the results were often less than satisfactory. Therefore, recently mathematical model and computer simulation are the other alternatives for robust design. However, Taguchi method and computer simulation have their own advantages and disadvantages. So, this idea motivates the approach of combining both advantages together to promote the more effectiveness of robust design. This paper proposes the approach to apply computer-aided engineering (CAE) with genetic algorithm (GA) and Taguchi method in dynamic robust parameter design. Firstly, we use computer simulation, CAE, to obtain the data instead of conducting whole real experiment. Next, a statistical approach, linear regression is used to model the unknown functions, and then GA, heuristics search approach, is employed to find the appropriate setting of controllable factors on the basis of the quality loss function. The effect of noise factors which is the important philosophy of robust design is also considered by utilizing the outer orthogonal array. The objective is to minimize the average quality loss instead of maximizing SN ratio. In addition, to enhance the capability of the proposed approach, the two-step method is applied to screen out the dispersion factors significantly affecting the quality variation and the adjustment factors significantly affecting the sensitivity of the Taguchi’s dynamic system for the case of changing products or processes’ requirements in the future. This proposed is applied to the example “Foam design of automobile’s dashboard”.

A robust tolerance optimization method based on fuzzy quality loss

Using the quality loss function developed by Taguchi, the manufacturing time and cost of a product can be reduced to improve the factory's competitiveness. However, the fuzziness in quality loss has not been considered in the Taguchi method. This article presents a fuzzy quality loss function model. First, fuzzy logic is used to describe the semantic of the quality, and the quality level is divided into several grades. Then the fuzzy quality loss function is developed utilizing the loss in monetary terms, which indicates the quality loss of each quality level and the normalized expected probability to each quality grade. Moreover, a new optimization model for tolerance design under fuzzy quality loss function is established. An example is used to illustrate the validity of the proposed model. The result shows that the proposed method is more flexible and can achieve the balance of quality and cost in tolerance design. It can be easily used in accordance with practical engineering applications.

Applying Taguchi method to determine the target values in goal programming

Setting the right target is of utmost importance in goal programming. An erroneous or an unreasonable target can lead to inferior solutions, resulting in misallocation of resources. This paper, using Taguchi's quality loss function proposes a systematic approach for setting an appropriate achievement level for goals in goal programming. The application of the proposed model is illustrated through a case study.

4.1.2 Product Upgrades Based on Minimum Expected Quality Loss

AbstractThe need to maintain or sustain a product's usefulness to or beyond its initial lifecycle expectancy is often driven by investment costs, market share, sales revenues, new product release schedules, standardization, uninterruptable usage, or declining budgets. A question then arises as to how often to upgrade a product. Aside from these typically discussed rationales, the paper concludes that a viable approach is to consider the upgrade cycle that results in the minimum cost based on quality. A general quality loss function was developed to investigate the expected quality loss for quality characteristics such as nominal‐the‐best, smaller‐the‐best, and larger‐the‐better. It is shown that when a shape parameter is introduced into the loss function, product upgrade cycles can be managed to minimize the expected losses.