Quality Loss Function Research Articles

An Interval Neural Network Method for Identifying Static Concentrated Loads in a Population of Structures

During the design and validation of structural engineering, the focus is on a population of similar structures, not just one. These structures face uncertainties from external environments and internal configurations, causing variability in responses under the same load. Identifying the real load from these dispersed responses is a significant challenge. This paper proposes an interval neural network (INN) method for identifying static concentrated loads, where the network parameters are internalized to create a new INN architecture. Additionally, the paper introduces an improved interval prediction quality loss function indicator named coverage and mean square criterion (CMSC), which balances the interval coverage rate and interval width of the identified load, ensuring that the median of the recognition interval is closer to the real load. The efficiency of the proposed method is assessed through three examples and validated through comparative research against other loss functions. Our research findings indicate that this approach enhances the interval accuracy, robustness, and generalization of load identification. This improvement is evident even when faced with challenges such as limited training data and significant noise interference.

Developing variables two-plan sampling scheme with consideration of process loss for lot sentencing

This paper considers a well-known two-plan sampling system, Tightened-Normal-Tightened (TNT) sampling scheme, which includes two single sampling plans (SSPs) with regulations for transitioning between tightened and normal inspections. Tightened inspection is conducted when there is a noticeable decline in quality, and normal inspection is employed when the quality is satisfactory. Most acceptance sampling plans evaluate product quality in terms of process yield, which does not differentiate between products that fall within specification limits. To address this issue, a new performance measure called the process loss index Le was developed, which accounts for the quality loss function. This index is determined by dividing the “expected quadratic loss” by the “square of half the specification width.” Using this index, two primary types of variables TNT sampling scheme were constructed and evaluated in this study. Their efficacy and features were investigated, discussed, and compared. The findings reveal that the TNT sampling strategy delivers the required quality assurance with a reduced sample size compared to the conventional SSP.

Arbitrary stylized light-field generation for three-dimensional light-field displays based on radiance fields.

Three-dimensional (3D) light-field display technology can reconstruct the spatial characteristics of 3D scenes and provide users with an immersive visual experience without the need for any additional external devices. Here, an arbitrary stylized light-field generation method for 3D light-field displays is presented, and the tripartite constraints are addressed by conducting style transformation in a refined feature space. A multi-dimensional feature refinement module is designed to learn which aspects and regions should be prioritized within the high-level feature grid of the scene, which allows content and style patterns to be better matched and blended. To preserve more structural details and reduce artifacts, a novel global quality and local structure joint loss function is used for optimization. A mask-guided light-field coding method based on ray-casting is employed to accelerate the synthesis of stylized light-field images. Experimental results demonstrate that the proposed method can generate higher-quality stylized 3D light-field content with any given style in a zero-shot manner. Additionally, the method provides two user control extensions to further enrich the ways for the personalized editing of 3D content displayed on 3D light-field displays.

Modelling a dense network connectivity for panoptic tooth segmentation using learning approaches

By enabling precise diagnoses and assisting in creating successful treatment regimens, teeth segmentation plays a crucial role in dentistry. The segmentation of teeth has been the primary emphasis of previous approaches, but they frequently ignore the context of the oral tissue as a whole. According to this study, background semantic and foreground instance-based segmentation results are combined in a panoptic-segmentation-based approach. This work provides a tailored architecture for segmenting using a Super Adaptive Dense Convolutional Neural Network (sa−DCNN) with a panoptic quality (PQ) loss function. The PQ loss function speeds up learning and enables the model to predict masks and the classes that go with them instantly. In our suggested design, sa−DCNN enables connectivity between the memory path and the sa−DCNN pixel route. A stacked network block integrating multi-scale properties from several decoding resolutions is also included. The network block's primary duties involve integrating various mechanisms. The output heads analyze the memory path and pixel route data to predict the mask classes used to create the final mask. The proposed model outperforms the most recent panoptic segmentation on the UFBA-UESC Dental Image dataset, notably in performance and resilience. Our study represents a significant advancement in teeth segmentation and advances our knowledge of oral anatomy.

A hybrid design for jointly optimizing production scheduling, control chart design and maintenance in continuous flow manufacturing

Integrating the three crucial functions of quality control, economic production quantity (EPQ) and maintenance leads to cost savings and increased efficiency for manufacturing processes. While in the literature, they have typically been studied separately. Moreover, most of the existing integration models are designed for the discrete piece-part manufacturing environment. This study, nevertheless, focuses wholly on continuous flow manufacturing (CFM), which is distinctly different from piece-part manufacturing, as the sampling unit is described in light of laboratory requirements instead of the production unit. Based on this fact, this paper proposes an integrated EPQ scheme jointly designed with control-chart design and maintenance planning for the CFM process. A developed genetic algorithm is employed to minimize the expected total production cost under constraints on the economic-statistical quality. Of the costs considered, quality-related costs are quantified via an approximate formula derived from the quality loss curve depending on Taguchi’s quality loss function. A sensitivity analysis is performed on the expected total production cost and variations in the chosen system parameter values to offer insights into the issue. Finally, a comparative investigation of the suggested model and two similar models that contributed to this field is conducted.

Research on Voltage Sag Loss Assessment Based on a Two-Stage Taguchi Quality Perspective Method

Voltage sags resulting from symmetrical or asymmetrical faults pose a significant threat to power quality. In response to this challenge, a voltage sag loss assessment method based on a two-stage Taguchi quality perspective approach is proposed to address the quantitative analysis of voltage sag economic losses. Initially, using the Taguchi quality perspective method, single-index quality loss functions are separately established for voltage sag magnitude and fault duration. Subsequently, by introducing a comprehensive load tolerance curve, sensitivity parameters within the quality loss function are accurately calculated. This yields a deterministic model for voltage sag assessment. Building upon this, the relative impact of the two indices on voltage sag loss is evaluated using the quality loss function. Consequently, a comprehensive loss model under the influence of multiple indices is formed by integrating two single-index evaluation models. The simulation results indicate that this method can effectively assess the economic losses of voltage sags under the combined influence of multiple factors. Compared to the original economic loss assessment method, it improves quantitative accuracy by approximately 3.72%. Moreover, the method reduces the computational complexity of loss assessment through the consolidation of intervals with similar sensitivity parameters.

Multi-Objective Optimization Design of Cycloid-Pin Gears Based on RV Reducer Precision Transmission Performance

This paper aims to realize multi-objective optimization of cycloid-pin gears to improve the positioning accuracy and load-carrying capacity of the rotary vector (RV) reducer, via the consideration of backlash, transmission error, and torsional stiffness. Initially, the analytical models of the RV transmission backlash and transmission error are developed by using both purely geometrical and equivalent model methods individually. Based on the generalized Hooke’s law, a torsion angle model is established to characterize the torsional stiffness of the system, utilizing methods such as Hertzian contact theory and bearing stiffness models. Subsequently, employing the Monte Carlo method, extremum method, and quality loss function, mapping objective functions for dimensional accuracy (tolerance) and transmission performance (backlash, transmission error, and torsional stiffness) are constructed. The geometry dimensions, dimensional accuracy, and modification of the cycloid-pin gear are considered as design variables to create a multi-objective optimization model. The improved Parallel Adaptive Genetic Algorithm using Deferential Evolution (PAGA-DE) is used for multi-objective solutions. Through example calculations, the impact of cycloid-pin gear parameters on transmission performance before and after optimization is determined. The reliability of backlash after optimization within 1.5′ reaches 99.99%, showing an increase of 8.24%. The reliability of transmission error within 1′ reaches 98.52%, demonstrating an increase of 1.35%. The torsional angle is reduced by 8.9% before optimization. The results indicate that the proposed multi-objective optimization design method for cycloid-pin gears can achieve the goal of improving the transmission performance of the RV reducer.

Multi-response robust parameter design based on Bayesian mixed effects model

In robust parameter design for blocked experiments, the correlation of response observations within each block and model parameter uncertainty often impact acquiring ideal operating conditions. In this paper, a Bayesian mixed regression-based multi-response surface modeling and optimization method is suggested to address the above issues. Firstly, the mixed effects model is incorporated into the Bayesian framework, and posterior distributions of the model parameters are derived using Bayes' theorem. Secondly, the hybrid Monte Carlo algorithm is employed to calculate the model parameters. Thirdly, the expected quality loss function satisfying the specification is constructed to lessen the impact of outliers on the results of optimization, and the optimal factor settings are obtained by the hybrid genetic algorithm. In addition, the posterior probability is used to assess the conformance of the optimization results. Finally, a simulated study and real-world example of the additive manufacturing process are used to illustrate the viability of the proposed method. Compared with the current techniques, the proposed method can reduce the impact of model uncertainty on the modeling and optimization results, leading to more conformant and robust optimization results.

Robust parameter design for 3D printing process using stochastic computer model

3D printing technology has been developing rapidly in recent years, but product quality control has become one of the main obstacles to its widespread use in manufacturing. A new stochastic computer model and robust optimization method are proposed for the highly fluctuating 3D printing process to improve the stability of the printed product quality. Firstly, the signal and noise are jointly modeled, and the idea of latent variables in machine learning is incorporated to overcome the limitation that the replication times of the stochastic Kriging model must be greater than one. Then, the chain rule and Woodbury identity are utilized to reduce the time required for hyperparameter estimation of the model. Finally, the optimization objective function is constructed based on the Taguchi quality loss function, and optimal process parameters are found using a genetic algorithm. The numerical simulation results demonstrate that the robust optimization method based on heteroskedasticity Gaussian process model proposed in this paper can estimate model hyperparameters faster and predict results more accurately. Furthermore, the prediction and validation results of 3D printing experiments verify the effectiveness of the proposed method.

Quantitative Evaluation Model of the Quality of Remanufactured Product

Remanufacturing is a significant process for achieving carbon neutrality. However, the existing literature shows that consumer concerns regarding the quality of remanufactured products restrict the large-scale development of the remanufacturing industry. Studies on the quantitative evaluation of the quality of remanufactured products are limited. Therefore, we propose a quantitative evaluation model of the quality of remanufactured products. Extended from the formation process of the quality of remanufactured products, the quality loss function of remanufactured parts and assemblies was constructed based on Taguchi's quality concept. Subsequently, the relationship among social loss, functional limit, and quality loss of remanufactured products was assessed. Accordingly, a quality measurement model of remanufactured products was established. Moreover, the parameter estimation algorithm based on a neural network was evaluated to deal with the dynamic changes and uncertainties of remanufacturing technology and the remanufacturing market. Finally, the application of the proposed model was demonstrated through a case study in which the quality of remanufactured engines was quantitatively evaluated. The relevance of the model was verified through market feedback. This article can provide practitioners and decision-makers with new and effective tools and insights to improve the quality of remanufactured products and reduce the cognitive gaps of customers. It is expected to accelerate the high-quality development of the remanufacturing industry.

A multinomial modeling approach to assess supplier delivery performance for buyer-supplier alignment

Purpose Untimely delivery of goods and services, especially in a post-COVID landscape, is a critical harbinger of end-to-end fulfillment. Existing literature in supplier delivery modeling is focused on penalizing suppliers for late deliveries built into a contractual transaction, which eventually erodes trust. As such, a holistic modeling technique focused on long-term relationship building is missing. This study aims to design a supplier evaluation model that analytically equates supplier delivery performance to cost realization while replicating a core attribute of successful supply chains – alignment, leading to long-term supplier relationships. Design/methodology/approach The supplier evaluation model designed in this paper uses delivery deviation as a unit of measure as opposed to delivery duration to enhance consistency with enterprise resource planning protocols. A one-sided modified Taguchi-type quality loss function (QLF) models delivery lateness to construct a multinomial probability penalty cost function for untimely delivery. Prescriptive analytics using simulation and optimization of the proposed mathematical model supports buyer–supplier alignment. Findings The supplier evaluation model designed herein not only optimizes likelihood parameters for early and late deliveries for competing suppliers to enhance total landed cost comparisons for on-shore, near-shore and off-shore suppliers but also allows for the creation of an efficient frontier toward supply base optimization. Research limitations/implications At a time of systemic disruptions such as the COVID pandemic, global supply chains are at risk of business continuity. Supplier evaluation models need to focus on long-term relationship modeling as opposed to short-term contractual penalty-based modeling to enhance business continuity. The model offered in this paper is grounded in alignment – a cornerstone of successful supply chain integration, and offers an interesting departure from traditional modeling techniques in this genre. Practical implications The results from this analytical approach offer flexibility to a supply manager toward building redundancies in the supply chain using an efficient frontier within the supply landscape, which also helps to manage disruption and maintain end-to-end fulfillment. Originality/value The model offered in this paper is grounded in alignment – a cornerstone of successful supply chain integration, and offers an interesting departure from traditional modeling techniques in this genre. The authors offer a rational solution by creating an evaluation model that uses penalty cost modeling as an internal quality measure to rate suppliers and uses the outcome as a yardstick for negotiations instead of imposing penalties within contracts.

Process machining allowance for reliability analysis of mechanical parts based on hidden quality loss

The machining allowance variation is significant for the reliability of a part during the machining process. Usually, when the machining allowance of a part increases, the machining and production cost also increase. When the machining allowance decreases, the machining surface will have defects. The parts will produce many scraps and reliability will decrease. The machining allowance of a part consists of multiple process machining allowances. To analyze the impact caused by machining allowance variation, the hidden quality loss and process machining allowance are combined through the process capability index (PCI). Then the asymmetric quadratic quality loss function (AQF) and quadratic exponential function (QEF) are used to analyze them. A prediction model of hidden quality loss of process machining allowance is proposed. On the premise that the quality characteristic value obeys normal function distribution, a numerical model is given and used to obtain process machining allowance-inherent reliability of the product. The actual case is used to compare and verify the two models.

Improvement of Quadratic Exponential Quality Gain–Loss Function and Optimization of Engineering Specifications

In the past, the optimization of engineering specifications primarily included the influence of quality loss terms on product quality; however, in actual production practice, compensation quantity inevitably affects the optimization quality of engineering specifications. In this paper, the quadratic exponential quality loss and gain function was first supplemented, and the quadratic exponential quality loss and gain function was constructed under the larger-the-better characteristic and the smaller-the-better characteristic; in order to accurately represent the change in compensation amount in the process of quality control, the optimization method of engineering specification under the calculation of quality loss and compensation was given in combination with the hyperbolic tangent function. Finally, with the support of the dam construction quality acceptance assessment, the engineering specification optimization model was tested. The optimal coefficient was obtained as 0.162, and the specification range was reduced from 0.744 to 0.648, achieving the optimization goal.

Mask-Transformer-Based Networks for Teeth Segmentation in Panoramic Radiographs.

Teeth segmentation plays a pivotal role in dentistry by facilitating accurate diagnoses and aiding the development of effective treatment plans. While traditional methods have primarily focused on teeth segmentation, they often fail to consider the broader oral tissue context. This paper proposes a panoptic-segmentation-based method that combines the results of instance segmentation with semantic segmentation of the background. Particularly, we introduce a novel architecture for instance teeth segmentation that leverages a dual-path transformer-based network, integrated with a panoptic quality (PQ) loss function. The model directly predicts masks and their corresponding classes, with the PQ loss function streamlining the training process. Our proposed architecture features a dual-path transformer block that facilitates bi-directional communication between the pixel path CNN and the memory path. It also contains a stacked decoder block that aggregates multi-scale features across different decoding resolutions. The transformer block integrates pixel-to-memory feedback attention, pixel-to-pixel self-attention, and memory-to-pixel and memory-to-memory self-attention mechanisms. The output heads process features to predict mask classes, while the final mask is obtained by multiplying memory path and pixel path features. When applied to the UFBA-UESC Dental Image dataset, our model exhibits a substantial improvement in segmentation performance, surpassing existing state-of-the-art techniques in terms of performance and robustness. Our research signifies an essential step forward in teeth segmentation and contributes to a deeper understanding of oral structures.

Robust optimization for functional multiresponse in 3D printing process

Computer models are commonly used to simulate the functional relationships between inputs and outputs for quality design in 3D printing. However, the high-dimensional outputs of functional multiresponse make it challenging to develop the simulation model and perform robust optimization. This paper proposes a novel optimization method with an additive multiresponse Gaussian process model for dealing with functional multiresponse optimization problems. First, an additive covariance function is constructed to capture the correlation of the temporal inputs. Second, the Markov Chain Monte Carlo sampling technique is adopted to determine the simulation model and quantify the uncertainty. Finally, the optimization model is constructed by integrating the quality loss function and interval analysis method, and the Bayesian optimization algorithm is used to obtain the optimal solution. A numerical simulation example and a 3D printing case study are used to illustrate the effectiveness of the proposed method. The comparison results show that the responses of the proposed method are closer to the targets than the current ones, and all fall within the specified interval.

Sustainable Quality Management Based on Metrological Sampling Scheme Design: A Case Study of Food Processor

The optimization of the sampling scheme is particularly important in order to achieve sustainability in quality management. This paper discusses the problem of optimizing the design of metrological sampling scheme when the mean is a random variable. Assuming that the prior distribution of product means is known, a Bayesian posterior probability is calculated by using the likelihood function with decision variables to measure the sampling risk, and the expected cost of the sampling scheme is calculated based on the protection of producer and user risk in combination with the Taguchi quality loss function. The influence of model parameters on the selection of the optimal sampling scheme is investigated through sensitivity analysis. The model constructed in this paper solves the problem of sampling design in the case of food processing enterprises, quantifies the quality loss of products in the sampling process, facilitates sustainable quality management of enterprises, and has important theoretical significance and application value for sustainable business management of food processing enterprises.

Concurrent optimization of parameter and tolerance design based on the two-stage Bayesian sampling method

ABSTRACT Researchers usually expect to reduce costs while improving product robustness in product quality design. The concurrent optimization of parameter and tolerance design assumes that the output response follows a normal distribution. However, non-normal responses are also common in product quality design. As for the concurrent optimization of parameter and tolerance design with a non-normal response, a novel total cost function based on the two-stage Bayesian sampling method is proposed in this paper. First, the hierarchical Bayesian model constructs the functional relationship between output response, input factors, and tolerance variables. Secondly, a two-stage Bayesian sampling method is used to obtain the simulated values of the output responses. The simulated response values are used to build the rejection cost and quality loss functions. Then, the genetic algorithm is used to optimize the constructed total cost model, including the tolerance cost, rejection cost, and quality loss. Finally, the effectiveness of the proposed method is demonstrated by two examples. The research results show that the proposed method in this paper can effectively improve product quality and reduce manufacturing costs when considering the uncertainty of model parameters and the variation of the output response.

Sand Supplier Selection Analysis Based on the Integration of Analytical Hierarchy Process (AHP) and Taguchi Quality Loss Function Methods

Supplier selection process is a step to evaluate and select the most suitable supplier to see the needs of the company or organization. This evaluation is important to ensure that the selected supplier is able to provide quality products or services, competitive prices, timely delivery, and meet ethical and sustainability standards. This research uses two methods, namely Analytical Hierarchy Process (AHP) and Taguchi Loss Function. AHP is used to calculate the weight of criteria, while the Taguchi Loss Function is used to estimate losses caused by suppliers. The criteria applied in supplier evaluation are quality criteria, product accuracy, delivery, price, warranty policy, and response to claims. The results obtained from this study PT. Bumi Makmur with a percentage loss of 21%, while the supplier that has the largest loss value is PT. Mergo Bopo with a percentage of 47%.
 Highlights :
 
 Integration of AHP and Taguchi Loss Function enhances supplier selection accuracy.
 Identified supplier exhibits substantial loss percentage, emphasizing the importance of thorough evaluation.
 Findings enable informed decision-making, facilitating risk mitigation and operational optimization
 
 Keywords :Supplier Evaluation; Sand; Analytical Hierarchy Process, Taguchi Loss Function

Optimization for waste coconut and fish oil derived biodiesel with MgO nanoparticle blend: Grey relational analysis, grey wolf optimization, driving training based optimization and election based optimization algorithm

The present work aimed at the practical utility of waste hybrid (coconut + fish oil) oil-derived biodiesel with magnesium oxide (MgO) nanoparticles (NPs) fuelled to diesel engines. Central composite design (CCD) experimental matrices with different sets of variables (blend type: 10–40 % vol. of biodiesel; MgO NPs: 60–180 ppm; engine speed: 1000–2000 rpm; engine load: 40–100 %) were used to examine the engine performance (brake specific fuel consumption: BSFC; and brake thermal efficiency: BTE) and emission characteristics (carbon monoxide: CO; unburnt hydrocarbon: UHC; nitrous oxide: NOx). The MgO NPs are characterized by using an X-ray diffractometer: XRD, scanning electron microscope: SEM and transmission electron microscope: TEM and confirm the compositions and the crystallite particle size equal to 132 nm. The models developed for each output showed a better value of coefficient of determination (R2) equal to 0.9843 for BSFC, 0.9859 for BTE, 0.9772 for CO, 0.9777 for NOx, and 0.9368 for UHC. Grey relational analysis (GRA) with quality loss function (QLFs) and principal component analysis (PCA) were used to correlate the multiple responses and transform multiple objective functions to single objective function necessary for optimization. Three population-based search algorithms, such as driving training-based optimization (DTBO) and election-based optimization algorithm (EBOA) and grey wolf optimization (GWO), were applied and evaluated their optimization performances. EBOA, DTBO and GWO determined the same optimal conditions and converged to 1000 iterations with a computational time equal to 2, 5 and 30 s, respectively. The algorithms determined optimal conditions produced better experimental values than GRA-based QLF and PCA with 31.27 % decrease in BSFC, 24.27 % decrease in CO, 4.64 % decrease in HC, 19.82 % decrease in NOx emissions, and 9.82 % decrease in BTE, respectively. MgO NPs addition to biodiesel fuel resulted in better performance and emission characteristics than without MgO NPs.

Robust optimization with uncertainty using a stochastic multivariate Gaussian process model

In robust parameter design (RPD), estimating the response surface model from the noisy experimental data is critical for parameter optimization. The multivariate Gaussian process (MGP) model has become a popular tool for response surface modelling. However, most existing MGP models may not effectively evaluate the uncertainty of noisy data. This article proposes a stochastic MGP for efficient emulation and robust optimization by considering uncertainty. Firstly, the hierarchical modelling technique is adopted to estimate the relationship model with noisy data. Secondly, the hyperparameters are estimated by the Gibbs technique, and the Bayesian averaging method is used to measure the parameter uncertainty. Finally, a novel optimization model integrated with the Bayesian averaging and quality loss function is developed to find the optimal solution. Two case studies are used to illustrate the effectiveness of the proposed method. The results show that the proposed approach obtains smaller quality loss than the existing ones.