Quality Of Manufactured Products Research Articles

Pattern recognition of control charts based on data feature enhancement and ensemble learning of classifiers for dimensional accuracy of products

Product quality in manufacturing is directly related to the reliability, durability and safety of the product. Product quality can be controlled by building a product control chart pattern recognition model. The complexity and temporal sequence of product quality data make it difficult to extract effective control chart features, and it is difficult for common classifiers to play an effective role for each control chart pattern category, thus affecting the accuracy of pattern recognition. Therefore, this paper proposes a data feature enhancement processing method that combines Smote algorithm and smooth shift processing. This method reveals data features by performing feature enhancement processing on raw data and extracts statistical and shape features for dimensionality reduction to improve recognition accuracy and efficiency. Based on this approach, this paper also proposes an ensemble learning model based on the Stacking method, which incorporates BP, ELM, PNN and SVM classifiers for control chart pattern recognition. Through extensive experimental validation, the data feature enhancement method improves the accuracy of the weak classifier normal pattern recognition by 30%, and effectively reduces the misclassification in the quality control process. The ensemble learning model is stronger than the weak classifier, and its recognition accuracy can reach 97.31%.

A branched Convolutional Neural Network for RGB-D image classification of ceramic pieces

From smart sensors on assembly lines to robots performing complex tasks, the fourth industrial revolution is rapidly transforming manufacturing. The growing prominence of 3D cameras in the industry has led the computer vision community to explore innovative ways of integrating depth and color data to achieve higher precision, essential for ensuring product quality in manufacturing. In this study, we introduce an innovative branched convolutional neural network designed to produce high-speed classification of multimodal images, such as RGB-Depth (RGB-D) images. The fundamental concept underlying the branched approach is the specialization of each branch as a dedicated feature extractor for a single modality, followed by their merge (intermediate fusion) to enable effective classification. Feeding our model is our novel multimodal dataset, named CeramicNet, composed of 8 classes that include RGB, depth, and RGB-D variations to enable extensive experimentation and evaluation of the models which, to the best of our knowledge, has not been previously introduced in the computer vision community. We conducted a series of experiments on the CeramicNet dataset. These experiments aimed at fine-tuning the model, assessing the influence of various depth technologies, exploring individual modalities, examining their collective impact, and performing comprehensive data analysis. Comparing our solution against seven widely used models, we achieved remarkable results, securing the top position with a precision of 99.89, with a lead of over 1% against the nearest competitor. What is more, the proposed solution yields an inference time of 127.6 ms — being nearly three times faster than the second-best performer.

Small-batch product quality prediction using a novel discrete Choquet fuzzy grey model with complex interaction information

With manufacturing focused on multi-variety and small-batch intelligent production, the challenge is to guarantee and ensure good product quality. This paper proposes a novel small-batch product quality prediction approach considering complex interaction information. In this paper, first, to handle the complex nonlinear correlations among the manufacturing process variables, a kernel principal components analysis is used to extract the major features from the high-dimensional data. Second, we combine the discrete multivariate grey model and generalized discrete Choquet fuzzy integral to propose a discrete Choquet fuzzy grey model so as to capture the complex interaction information among the process variables. Next, an adjoint sensitivity analysis is applied to characterize the changes in the process variables on the predicted product quality index. We conduct an experiment on six semiconductor products made in China to validate the proposed model against a library of nine other methods. Our model yields an average reduction of 11.02% on MAPE, 20.47% on MSE, 13.56% on STD, and an average increase of 46.37% on EVS for six types of products. Our results inform that the proposed model is suitable for predicting manufacturing product quality when the process variables interact significantly, and we can prioritize the process variables for remedial action accordingly.

Surface Defect Detection: A feature-based transfer learning approach

Surface defect detection is critical for maintaining product quality in manufacturing. In this work, we apply a feature-based transfer learning approach for surface defect classification on the NEU surface defect database. The database contains defects across 6 categories captured under various conditions. We utilised two pretrained convolutional neural network (CNN) architectures - VGG16 and InceptionV3 - by removing the final classification layer and using the CNN as a fixed feature extractor. The output feature vectors were classified using a logistic regression (LR) model. The data was split into train, validation, and test sets with a 70:15:15 ratio. The VGG16-LR model achieved classification accuracy (CA) of 100%, 98%, and 99% for the train, validation, and test sets respectively. The InceptionV3-LR model attained CA of 100%, 91%, and 92% for train, validation, and test. The results demonstrate the effectiveness of transfer learning with CNN feature extraction for surface defect detection on challenging multi-category industrial datasets. Further work includes tuning hyperparameters and evaluating additional architectures.

Reliability-oriented product manufacturing quality improvement approach based on R-KQC and DMAIC

ABSTRACT Reliability-oriented product quality improvement is of great significance to assurance the fitness of quality control and management activities in the manufacturing process. A novel reliability-oriented product manufacturing quality improvement approach based on DMAIC (i.e. define, measure, analysis, improvement, control) and driven by reliability-oriented key quality characteristic (R-KQC) is proposed to prevent reliability degradation and improve product fitness quality in the manufacturing process. First, with the manufacturing reliability based on RQR chain taken into consideration, the connotation of R-KQC is defined. Second, a reliability-oriented DMAIC process driven by R-KQC is proposed. The R-KQC identification method based on feature selection and Shaply additive explanations (SHAP) is proposed. In order to improve the quality of manufacturing process effectively, R-KQC improvement method of response surface and R-KQC control method based on time-between-events (TBE) control chart are proposed. Finally, an illustrated example of an insulating base is provided to verify the effectiveness of the proposed approach, the average failure rate of the latest batch is reduced by 37.8%.

Traditional or drop-shipping? channel choice and product quality

Compared to the traditional channel, where a retailer bears the inventory risk, the drop-shipping channel operates with a distinct approach: the retailer avoids stocking products while the manufacturer directly handles stocking and shipping to consumers. Due to the different inventory risk allocations, the two channels have different product qualities and profits for the manufacturer and retailer. In this study, we investigate product quality decision of the manufacturer and delve into the impact of product quality on the manufacturer's and retailer's profitability. First, we find that product quality can be weakly higher in the drop-shipping channel than that in the traditional channel. This is because the drop-shipping channel allows the manufacturer who undertakes demand uncertainty to charge a higher wholesale price, resulting in a higher product quality. Second, our study reveals that the traditional channel can concurrently yield higher profits for the manufacturer and retailer when product quality is considered, which is in contrast to the previous works. Third, in the traditional channel, as demand uncertainty rises, the retailer's production quantity increases, while the manufacturer's product quality decreases. Finally, our results indicate that the product quality is more sensitive to the shipping cost when demand uncertainty is low.

Edge computing-based proactive control method for industrial product manufacturing quality prediction

With the emergence of intelligent manufacturing, new-generation information technologies such as big data and artificial intelligence are rapidly integrating with the manufacturing industry. One of the primary applications is to assist manufacturing plants in predicting product quality. Traditional predictive models primarily focus on establishing high-precision classification or regression models, with less emphasis on imbalanced data. This is a specific but common scenario in practical industrial environments concerning quality prediction. A SMOTE-XGboost quality prediction active control method based on joint optimization hyperparameters is proposed to address the problem of imbalanced data classification in product quality prediction. In addition, edge computing technology is introduced to address issues in industrial manufacturing, such as the large bandwidth load and resource limitations associated with traditional cloud computing models. Finally, the practicality and effectiveness of the proposed method are validated through a case study of the brake disc production line. Experimental results indicate that the proposed method outperforms other classification methods in brake disc quality prediction.

Enhancing Efficiency and Cost-Effectiveness: A Groundbreaking Bi-Algorithm MCDM Approach

Numerous scholars have thoroughly studied the topic of choosing machines considering the progress and technological growth seen in machinery options. This scholarly investigation explores decision-making methods specifically designed to aid the selection of machines in manufacturing businesses. Additionally, this research emphasizes the need for decision-making frameworks in manufacturing facilities, highlighting the importance of smart machine selection strategies in those contexts. In this research, we show a dual-MCDM approach that includes DEX—decision experts—and the EDAS method that are popularly employed to solve decision-making problems in both academic and practical industries. Throughout the previous decade, business leaders and managers increasingly use MCDM solutions to overcome machine selection challenges. At this time, while various decision-support technologies and procedures have been developed and used, it is essential that we discuss the sequence of our study objectives and drive the proposed method for widening use in practical firms. In short, this research may be helpful as a literature review for MDCM studies and related topics. It will also help executives, engineers, and specialists determine which equipment or machines to create and increase product quality in manufacturing and industry.

Detection of Glycolytically Active Lacticaseibacillus paracasei Strain Shirota by Flow Cytometry Targeting the Efflux Activity of Fluorescent Dye: a Potential Tool for Quality Assessment of Probiotic Cells in Milk Products.

The rapid and accurate detection of viable probiotic cells in dairy products is important for assessing product quality in manufacturing. Flow cytometry is widely used for the rapid analysis of bacterial cells. However, further investigation is needed into the optimum property to use it for assessing cell viability. Here, we proposed using the efflux activity of a fluorescent dye, carboxyfluorescein (CF), as an indicator of cell viability. CF is generated from 5(6)-carboxyfluorescein diacetate as a result of cleavage by intracellular esterase. It generally accumulates in the cell, but certain bacterial species are known to extrude it. We found here that the probiotic strain Lacticaseibacillus paracasei strain Shirota (LcS) also extruded CF in the presence of energy sources, such as glucose. To investigate the mechanism of its CF-efflux activity, we screened CF-efflux-negative mutants from a random mutagenesis LcS library and examined the whole genome for genes responsible for CF efflux. We identified a base substitution in the pfkA gene in the glycolytic pathway, and we demonstrated that intact pfkA was essential for CF efflux, indicating that CF-efflux-positive cells must have uncompromised glycolytic activity. We also confirmed that there was a good correlation between the rate of CF-efflux-positive cells and that of colony-forming cells of LcS in a fermented milk product, whereas other properties, such as esterase activity and cell membrane integrity, lost their correlation with the colony-forming activity after long storage. We propose that CF-efflux activity could be an appropriate indicator of cell viability in certain probiotic strains. IMPORTANCE To our knowledge, this is the first report to demonstrate that CF efflux requires uncompromised glycolytic activity in certain lactic acid bacteria. Compared with the cell properties currently widely used for cell viability assessment, such as intracellular esterase activity and membrane integrity, CF-efflux activity enables the accurate detection of culturable cells, especially in products stored for long periods at cold temperatures. These results indicate strongly that CF-efflux activity can be an adequate cell-viability indicator and that flow cytometric quantification could be an alternative to conventional CFU counting. Our findings should be especially informative for dairy/probiotic product manufacturing.

Horizontal and vertical demand forecast information sharing in a distributive dual‐channel supply chain considering the manufacturer's product quality improvement

AbstractUnder the influence of market demand uncertainty, we discuss the issue of horizontal and vertical demand forecast information‐sharing in a distributive dual‐channel supply chain composed of a manufacturer, a traditional retailer and an online retailer in which both retailers obtain heterogeneous demand information through big data technology. We analyze vertical information‐sharing strategies in the condition that the manufacturer invests in product quality improvement under different horizontal information‐sharing scenarios. We also explore the value of horizontal information‐sharing across different channels through contrastive analysis. And the equilibrium information‐sharing states in different scenarios are conducted.

Online prediction of automotive tempered glass quality using machine learning

This study explores the application of machine learning algorithms for supporting complex product manufacturing quality through a focus on quality assurance and control. We aim to take advantage of ML technics to solve one of the complex manufacturing problems of the tempered glass manufacturing industry as a first attempt to automate product quality prediction and optimization in this industrial field as an alternative to destructive testing methodologies. The choice of this application field was motivated by the lack of a robust engineering technique to assess the production quality in real time; this arises the need of using advanced smart manufacturing solution as AI to save the extremely high cost of destructive tests. As methodology, this paper investigates the performance of machine learning techniques including Ridge Regression, Linear Regression, Light Gradient Boosting Machine, and Lasso Regression, for predicting the product thermal treatment quality within the selected type of industry. In the first part, we applied the selected machine learning models to a dataset collected manually and made up of the more relevant process parameters of the heating and the quenching process. Evaluating the results of the applied models, based on several performance indicators such as mean absolute error, mean squared error, and r-squared, declared that Ridge Regression was the most accurate model with a mean error of 14.33 which is significantly acceptable in a business point of view and not reachable by any human level experience of prediction. The second part consists of developing a digitalized device connected to the manufacturing process to provide predictions in real time. This device operates as an error-proofing system that sends a reverse signal to the machine in case the prediction shows a non-compliant quality of the current processed product. This study can be expanded to predict the optimal process parameters to use when the predicted values do not meet the desired quality and can advantageously replace the trial-and-error approach that is generally adopted for defining those parameters. The contribution of our work relies on the introduction of a clear methodology (from idea to industrialization) for the design and deployment of an industrial-grade predictive solution within a new field which is the glass transformation.

Measurement and Metrology in Advanced Manufacturing Processes

New and improved measurement methods are paramount to ensure in-process monitoring of advanced manufacturing processes and quality products. This editorial discusses the outline of the special issue consisting of 15 peer-reviewed manuscripts in the domain of "Measurement and Metrology in Advanced Manufacturing Processes." These research and review articles discuss the relevance, state-of-the-art methods, and ongoing research on the advancement of manufacturing processes with measurements and metrology perspectives by different research groups globally. The significance of measurement and metrology is recognized in various applications such as additive manufacturing, photopolymer jetting, submerged arc welding, micro-electrical discharge machining, and reverse manufacturing.

Determination of parameters of a trepanning machine for cleaning wool fibers

This article provides information about the technology of primary processing of wool and the feeding part of the baking machine. It analyzes the operating principle and types of baking machines at the enterprise of primary processing of wool. The disadvantages of baking machines affecting the product are considered. The principle of work and the design of new baking machines for the manufacture of quality products are proposed. The article provides information about the technology of primary processing of wool. Studied the mechanisms of machines for the production of wool and identified their design flaws. The designs and sizes of the pegs of the peg drum are analyzed. The designs of the loosening machines used in the loosening process were studied. The types and principles of baking machines working at the enterprises of primary processing of wool are analyzed. The technical characteristics of the machines are given. The negative aspects of the details of the mechanical impact on the product are noted. Defects of baking machines and their effect on the product are explained. The design and operational principle of a new spraying machine for the preparation of high-quality products is proposed. The proposed characteristics of the machine have high performance, structural design, impact on the product, low energy consumption, energy efficiency and effective loosening. In this machine, the optimal version of parts that have a positive effect on the natural characteristics of the product is selected. The designs of the loosening machines used in the loosening process were studied. The types and principles of baking machines working at the enterprises of primary processing of wool are analyzed. The technical characteristics of the machines are given. The negative aspects of the details of the mechanical impact on the product are noted. Defects of baking machines and their effect on the product are explained. The design and operational principle of a new spraying machine for the preparation of high-quality products is proposed. The proposed characteristics of the machine have high performance, structural design, impact on the product, low energy consumption, energy efficiency and effective loosening. In this machine, the optimal version of parts that have a positive effect on the natural characteristics of the product is selected.

Solving a multi-objective distributed scheduling problem for building material equipment group enterprises by measuring quality indicator with a product gene evaluation approach

In building material equipment group enterprises (BME-GEs), unstable manufacturing quality and insufficient delivery capacity are the common problems, where their on-time delivery capacity is greatly affected by manufacturing quality. Therefore, improving manufacturing quality control ability is the key approach to improve their core competitiveness. The manufacturing quality of a product is determined by the attributes of multiple manufacturing resources, therefore, optimizing the utilization of manufacturing resources can improve product manufacturing quality and reduce quality problems in BME-GEs, so as to reduce delivery delay caused by quality problems. Aiming at achieving the goal mentioned above, we were inspired by biological genetic engineering, and a product gene recombination mechanism was analyzed and designed based on our existing studies on product gene. And a multi-objective scheduling model considering minimizing total costs and makespan while maximizing quality for the distributed collaborative manufacturing mode of BME-GEs was established, where a comprehensive measurement method of quality according to our research on product gene evaluation method was presented. To deal with the multi-objective problem, the Fuzzy Analytic Hierarchy Process (FAHP) was applied to determine the weight of each objective. To solve the above model, a hybrid genetic algorithm and discrete particle swarm optimization (H-GA-DPSO) based on multi-level encoding method was designed, which optimized the operation-sequencing, job-to-cell assignment and operation-to-machine assignment by considering the frequent operation outsourcing in BME-GEs. To verify the performance of the above model and algorithm, several comparison experiments including tabu search (TS), GA, DPSO and H-GA-DPSO were presented. The results indicate that the proposed model and algorithm can effectively solve the optimization problem of manufacturing resources in BME-GEs, and compared with the three single algorithms, the hybrid algorithm has significant advantages on optimization ability as well as comprehensive performance for solving the problem studied in this research.

ОЦІНЮВАННЯ ВТРАТ РОБОЧОГО ЧАСУ У ВИРОБНИЧИХ СИСТЕМАХ І СТАБІЛЬНОСТІ РОБОТИ АВТОМАТИЧНИХ ЛІНІЙ У ГАЛУЗІ ДЕРЕВООБРОБЦІ

The paper analyzes a new method of calculating additional losses of working time in sequential layout systems, considers the problem of applying modern methods of calculating automated production systems to improve the efficiency of woodworking enterprises. The influence of stochastic factors on the stability of technological operations is analyzed. Additional imposed losses of working time significantly reduce the efficiency of production systems as a whole. In the woodworking industry, technological operations have little stability, so the imposition of loss of working time is particularly pronounced. The actual performance of automated lines is significantly reduced. Improving the productivity of technological lines is performed by developing optimal equipment layout schemes, structural and parametric optimization. An important task is to calculate the component costs of the production process and losses of working time in order to improve production efficiency and manufacture quality products. Existing methods for estimating the imposition of loss of working time are approximate and suitable only for production systems with the same sites. In the case of a large number of consecutive production sites with different nominal productivity, an approximate estimate of the loss of working time is performed using the appropriate calculations used for the two sites. In subsequent calculations, a conditional section is created, which interacts with the next section, the parameters of the new section are calculated and so the calculation is carried out to the end of the production line. For complex production systems, simulation of line operation is performed.

Product quality control strategy of dual distribution channel structure in three-echelon supply chain

Based on the three-stage Stackelberg dynamic game model, we study how to make product quality control strategy in the three-echelon supply chain consisting of the manufacturer, retailer and customer under retailer dual-channel structure and manufacturer dual-channel structure. In two decision models (decentralized decision, centralized decision), we analyze the demand price elasticity, market share ratio, revenue sharing ratio and quality cost coefficient how to influence the product demand, product quality level, retail price and direct price in different channels, expected revenue functions of manufacturer and retailer, consumer surplus and product quality control strategy. We find that firstly, the retail price and direct price are positively related to product quality level, and the product quality level is negatively related to the demand price elasticity in traditional retail channel and the demand price elasticity in internet channel. What's more, the retailer’s retail price in traditional retail channel will be higher than direct price in internet channel. Thirdly, in the case of centralized decision, the manufacturer's product quality level, retail price, joint expected revenue and consumer surplus will all rise, but the direct price will fall. Fourthly, when the manufacturer entrusts the third-party platform to build the internet channel, the manufacturer's product quality level, retail price, direct price, expected revenue, and consumer surplus will all decrease. Finally, we conduct the simulation analysis by MATLAB 2018, which verifies the validity and credibility of our conclusions and points the direction for the specific application of the model in practice.

Teaching Factory Learning Model as Income Generating Unit with Marketable Products in Public Vocational High School

Vocational High School (VHS) is a vocational school intended to give students practical skills to create skilled graduates ready for jobs. To serve this purpose, Public Vocational High School (PVHS) 1 of Jenangan designs teaching factory learning model. Teaching factory is a learning model focusing on teaching students some practical skills with which to manufacture quality products up to industry standard. Hopefully, the educational outcome of this model can be Income Generating Unit (IGU) of software engineering study program in the school. This is descriptive and qualitative research using Miles ad Huberman’s data analysis model. The research found that using teaching factory as income generating unit with marketable products in software engineering study program is an effective strategy for the effort to provide quality human resources ready to perform jobs and create marketable products.

Design Artificial Intelligence Fiber Testing System Aided by Computer

With the progress and development of society, in people’s wardrobes, textile clothing belongs to a category of clothing that is used in people’s daily life, and textiles for household goods also occupy most of the market. And with the increasing diversification of textile raw materials, it is more and more important to strengthen the detection of fiber content in textiles. There are many methods for determining fiber content in textiles. In fact, in the fiber inspection process, the high-speed camera can not recognize the image of the fiber surface. Computer-aided image processing and deep learning algorithms are used to realize computer-aided recognition through a series of inspection processes. Computer-aided technology has strong interaction and high accuracy, while artificial intelligence fiber testing technology has great responsibility for product manufacturing. Product model and simulation have an impact on product manufacturing quality and work efficiency. The artificial intelligence fiber testing system and computer-aided technology must be combined to improve the quality of the fiber purchased or sold, so as to obtain higher income for enterprises and provide better services for people. How to use computer-aided technology to serve the design of artificial intelligence fiber testing system to improve the user experience of the system is the purpose of this thesis. This article will discuss the general situation of artificial intelligence fiber testing system, the analysis of computer-aided technology in artificial intelligence fiber testing system, and the application analysis of computer-aided technology in artificial intelligence fiber testing system.

HerBChain, a blockchain-based informative platform for quality assurance and quality control of herbal products

The use of medicinal plants is popular worldwide. Correct herbal authentication is of paramount importance to the safety and best interest of consumers. On the market, there is no comprehensive blockchain-based system to track the processes from plantation to manufacturing and to the sale. With the advancement of information technology, an open and transparent blockchain-based platform, HerBChain, was created to enhance the quality control of herbal products. The implementation of blockchain technology is to minimize the manipulation of recorded information. HerBChain is an information platform for recording the six important processes of herbal product manufacturing and marketing, which include plantation base, TCM processing factory, TCM manufacturer, testing laboratory, distributor and retailer. By duly recording the parameters and data essential for product quality in manufacturing and supply chain, the traceability and reliability of the products can be ensured.

Evironmental Accounting Disclosure And Financial Sistainability In Listed Negerian Manufacturing Firms

With the globalization and dynamic nature of the competitive market environment, manufacturing of quality products at affordable prices no longer guarantee sustainable financial performance, hence firms are now running to sustainability measures to remain financially sustainable. However, manufacturing firms in Nigeria has failed to sustain their performance. Thus, the study was initiated to evaluate the effect of environmental accounting disclosures on financial sustainability of listed Nigerian manufacturing firms. Ex-post facto research design using annual reports of 10 listed manufacturing firms was adopted to achieve the objective of the study. Data was measured using multiple regression analysis. The study revealed that environmental accounting disclosures has insignificant but positive effect on financial sustainability of listed manufacturing firms in Nigeria (Adj. R2 = 0.0468, F- statistics = 1.9721, P-value = 0.0899). With the introduction of the moderating effect of firm size, environmental accounting disclosures showed insignificant but positive effect on financial sustainability of listed manufacturing firms in Nigeria (Adj. R2 = 0.0489, F- statistics = 1.8487, P-value = 0.0981). Thus, the study concluded that environmental accounting disclosures do not have positive but insignificant effect on financial sustainability. It is recommended that the accounting profession should develop standards for reporting environmental accounting information by business entities. At the firm level, there should be voluntary disclosures of environmental accounting information.