Quality Control Of Products Research Articles

Low-contrast X-ray image defect segmentation via a novel core-profile decomposition network

Accurate X-ray image defect segmentation is of paramount importance in industrial contexts, as it is the foundation for product quality control and production safety. Deep learning (DL) has demonstrated powerful image scene understanding capabilities and has achieved unprecedented performance in defect segmentation tasks. However, existing DL methods suffer from significant performance degradation when facing low-contrast X-ray images, as the core information of defects is often obscured and the profile details are ambiguous. To address this issue, this paper explicitly decomposes the X-ray defect segmentation task into two subtasks: core feature learning and elasticity profile refinement, allowing task “serial” decomposition and performance “parallel” improvement. On this basis, a novel core-profile decomposition network (CPDNet) is developed to achieve accurate defect segmentation of X-ray images. Specifically, the core feature learning module is designed to construct the effective feature space from two views, discriminative and structural, to extract defect-related core features from X-ray images. Subsequently, the elasticity profile refinement module is developed to further improve the defect segmentation performance, which makes the first attempt to define the profile refinement as an out-of-distribution detection and leverage the elasticity score to refine the profile details at the pixel level. To fully evaluate the presented method, we conduct a series of experiments using two real-world X-ray defect datasets, and the results demonstrate that the CPDNet outperforms state-of-the-art methods.

Retraction Note: Research on hot-rolling steel products quality control based on BP neural network inverse model

Retraction Note: Research on hot-rolling steel products quality control based on BP neural network inverse model

Application of Advanced Deep Learning Models for Efficient Apple Defect Detection and Quality Grading in Agricultural Production

In this study, a deep learning-based system for apple defect detection and quality grading was developed, integrating various advanced image-processing technologies and machine learning algorithms to enhance the automation and accuracy of apple quality monitoring. Experimental validation demonstrated the superior performance of the proposed model in handling complex image tasks. In the defect-segmentation experiments, the method achieved a precision of 93%, a recall of 90%, an accuracy of 91% and a mean Intersection over Union (mIoU) of 92%, significantly surpassing traditional deep learning models such as U-Net, SegNet, PSPNet, UNet++, DeepLabv3+ and HRNet. Similarly, in the quality-grading experiments, the method exhibited high efficiency with a precision of 91%, and both recall and accuracy reaching 90%. Additionally, ablation experiments with different loss functions confirmed the significant advantages of the Jump Loss in enhancing model performance, particularly in addressing class imbalance and improving feature learning. These results not only validate the effectiveness and reliability of the system in practical applications but also highlight its potential in automating the detection and grading processes in the apple industry. This integration of advanced technologies provides a new automated solution for quality control of agricultural products like apples, facilitating the modernization of agricultural production.

Food Rheology: An Introduction and Fundamentals Concepts

Food rheology is the study of the flow and deformation of food materials. It involves understanding the physical and mechanical properties of food, such as how it behaves when subjected to external forces or changes in temperature. Understanding food rheology is essential in various food processing and manufacturing industries as it helps in product development, quality control, and optimization of processing parameters. Some fundamental concepts in food rheology include as follows. Viscosity refers to a material’s resistance to flow. In food rheology, it is a measure of how easily a food material flows under an applied force. Food materials can exhibit different types of viscosity, such as Newtonian, pseudoplastic, dilatant, and viscoelastic behavior. Shear stress is the force per unit area applied to a food material, while the shear rate is the rate at which the food material deforms. In food rheology, these two variables are used to describe the flow behavior of food materials. Different food materials have different flow behaviors. Some foods, like water, exhibit Newtonian flow behavior, where the viscosity remains constant regardless of the applied shear rate. Other foods, like ketchup or mayonnaise, exhibit non-Newtonian flow behavior, where the viscosity changes with the shear rate. Elasticity refers to a material’s ability to regain its original shape after deformation. In food rheology, elasticity is important in determining the texture and shelf life of food products. Viscoelasticity refers to the combined properties of both viscosity and elasticity, where a material exhibits both liquid-like (viscous) and solid-like (elastic) behavior. Yield stress is the minimum amount of shear stress required to initiate flow in a material. Many food materials, such as gels or semisolid foods, exhibit yield stress where they behave like a solid until a certain stress threshold is reached. By understanding these fundamental concepts, food scientists and engineers can manipulate and control the rheological properties of food materials to achieve the desired texture, mouthfeel, and sensory attributes, as well as optimize processing conditions to improve the overall quality of food products.

Phase Transformation of AlV55 Alloy at High Temperature

Vanadium–aluminum alloy is an important intermediate alloy for preparing aviation grade titanium alloys, and its product quality directly affects the finished product quality of titanium alloys. In this study, focusing on the problems of high powder content (19.8%) and low product yield in AlV55 alloy products, we conduct research on alloy quality control technology and implement a vanadium–aluminum alloy cooling crystallization control process. The research results indicate that there are three phases in AlV55 alloy, namely Al8V5, AlV, and Al2V3 phases. As the temperature decreases, the AlV phase gradually decomposes into Al8V5 phase and Al2V3 phase, and the proportion of Al8V5 phase is positively correlated with the fineness. Rapid cooling can reduce the formation of Al8V5 phase. The experimental results show that high-temperature water quenching can increase the proportion of vanadium–aluminum solid solution phase in the alloy from 19.03% to 31.76%, and reduce the fine powder rate to 13.2%, providing important product quality control means and technical support for the production of vanadium–aluminum alloys.

Rapid Mass Spectrometry-Based Multiattribute Method for Glycation Analysis with Integrated Afucosylation Detection Capability.

The multiattribute method (MAM) has emerged as a powerful tool for simultaneously screening multiple product quality attributes of therapeutic antibodies. One such potential critical quality attribute (CQA) is glycation, a common modification that can impact the heterogeneity, functional activity, and immunogenicity of therapeutic antibodies. However, current methods for monitoring glycation levels in MAM are rare and not sufficiently rapid and accurate. In this study, an improved mass spectrometry (MS)-based MAM was developed to simultaneously monitor glycation and other quality attributes including afucosylation. The method was evaluated using two therapeutic antibodies with different glycosylation site numbers. Treatment with IdeS, Endo F2, and dithiothreitol generated three distinct subunits, and the glycation results obtained were similar to those treated with PNGase F, which is routinely used to release glycans; the sample processing time was greatly reduced while providing additional quality attribute information. The MS-based MAM was also employed to assess the glycation progression following forced glycation in various buffer solutions. A significant increase in oxidation was observed when forced glycation was conducted in an ammonium bicarbonate buffer solution, and a total of 23 potential glycation sites and 4 significantly oxidized sites were identified. Notably, we found that ammonium bicarbonate was found to specifically stimulate oxidation, while glycation had a synergistic effect on oxidation. These findings establish this study as a novel methodology for achieving a technologically advanced platform and concept that enhances the efficacy of product development and quality control, characterized by its broad-spectrum, rapid, and accurate nature.

Optimal harvest period and quality control markers of cultivated Flos Chrysanthemi Indici using untargeted/targeted metabolomics, chemometric analysis and in vivo study

Ethnopharmacological relevanceFlos Chrysanthemi Indici (FCI), the flower of Chrysanthemum Indicum L., is a popular traditional Chinese medicine (TCM) for treatment of inflammatory diseases in China. FCI is also a functional food, and is widely used as herbal tea for clearing heat and detoxicating. Aim of the studyTo explore quality control markers of FCI based on the optimal harvest period. Materials and methodsFirst, UPLC-Q-TOF/MS based untargeted metabolomics was applied to explore the chemical profiles of FCIs collected at bud stages (BS), initial stages (IS), full bloom stages (FS) and eventual stages (ES) from eight cultivated regions in China. Subsequently, lipopolysaccharide (LPS)-induced RAW264.7 cell inflammatory model and carrageenan-induced rat paw edema model were used to confirm the anti-inflammatory effect of FCIs collected at IS/FS. Then, UPLC-PDA targeted metabolomics was used to quantitatively analyze 9 constituents with anti-inflammatory activity (7 flavonoids and 2 phenolic acids) changed significantly (VIP > 4) during flowering stages. Finally, ROC curves combined with PCA analysis based on the variation of 9 active constituents in FCIs from different flowering stages were applied to screen the quality markers of FCI. ResultsFCIs at IS/FS had almost same chemical characteristics, but quite different from those at BS and ES. A total of 32 constituents in FCIs including flavonoids and phenolic acids were changed during flowering development. Most of the varied constituents had the highest or higher contents at IS/FS compared with those at ES, indicating that the optimal harvest period of FCI should be at IS/FS. FCI extract could effectively suppress nitric oxide (NO) production in LPS-induced RAW264.7 cells and regulate the abnormal levels of cytokines and PGE2 in carrageenan-induced paw edema model rat. The results of quantitatively analysis revealed that the variation trends of phenolic acids and flavonoids in FCIs were different during flowering development, but most of them had higher contents at IS/FS than those at ES in all FCIs collected from eight cultivated regions, except one sample from Anhui. Finally, linarin, luteolin, apigenin and 3,5-dicaffeoylquinic acid were selected as the Q-markers based on the contribution of their AUC values in ROC and clustering of PCA analysis. ConclusionsOur study demonstrates the optimal harvest period of FCI and specifies the multi-constituents Q-markers of FCI based on the influence of growth progression on the active constituents using untargeted/targeted metabolomics. The findings not only greatly increase the utilization rate of FCI resources and improve quality control of FCI products, but also offer new strategy to identify the Q-markers of FCI.

O-209 Identifying toxicity trends: analysis of over 6700 Mouse Embryo Assays performed on 16 categories of IVF supplies

Abstract Study question What type of disposables and solutions exhibit a higher frequency of Mouse Embryo Assay (MEA) failure and where should manufacturers put special attention during production? Summary answer Flexipet-pipette types, protein supplements, ovum-pick-up needles, catheters, steripettes, culture media, and mineral oils showed higher MEA-failure frequencies and/or lethality levels due to embryotoxicity among IVF-supplies. What is known already The MEA is considered the gold standard assay for quality control of IVF products. It is based on the analysis of in vitro mouse embryonic development under direct or indirect presence of a to-be-tested product, and it requires over 80% expanded blastocyst formation rates (EBFRs) for a product to be considered non-toxic and be released to the market. Recent episodes reported toxicity issues found in embryo culture supplies and IVF industry devices that were recalled by manufacturers. This underscores the necessity for more specific characterization of products, guidelines, and rigorous quality control protocols to prevent potentially adverse clinical outcomes. Study design, size, duration MEAs were conducted over 5 years on 6759 batches encompassing 16 categories of IVF products from various manufacturers. Results were retrospectively analysed based on MEA test outcomes for each category. A total of 217 dishes, 610 catheters, 1182 culture media, 135 steripettes, 1907 mineral oils, 167 glass-pasteur pipettes, 66 protein supplements, 207 flexipet-pipettes, 191 pipette tips, 96 PVPs, 68 syringes, 126 tubes, 1294 vitrification kits, 182 micropipettes, 98 disinfectants, and 213 needles lots were analysed. Participants/materials, setting, methods All procedures adhered to protocols approved by an Ethical Committee. Samples underwent classification as toxic or non-toxic based on MEAs results, and the proportion of samples that tested positive for embryotoxicity was determined for each category. Statistical comparisons were made among categories to identify those most prone to be identified as toxic. Additionally, in failed assays, mean EBFRs were categorized into 0-30%, 30%-70%, and 70%-80% ranges to assess extreme, mild and low sample-toxicity levels, respectively. Main results and the role of chance Out of 16 studied categories, only 5 of them exceeded a 5% of toxic lots. Flexipet-pipette types were reported as the highest toxic-samples rate category, with 72 out of the 207 tested batches (34.8%) failing the MEA. Protein supplements were found to be the second highest toxicity-ranked category, with 14/66 noxious lot samples (21.2%). They were followed by needles and catheters with 36/213 (16.9%) and 68/610 toxic lot samples (11.2%), respectively. Finally, a considerably lower toxicity rate was obtained with steripettes, with 10/135 samples reported as toxic (7.4%). Among these five top toxic-samples rate categories, protein supplements were found to possess a mild lethal effect on embryos, with a 43.6% mean EBFR in failed assays. However, extreme embryotoxic effects were reported for the remaining highest toxic-samples rate categories, based on their mean EBFR in failed assays: 20.8% for flexipet-pipette types, 16.2% for needles, 10.8% for steripettes, and 10.3% for catheters. Interestingly, although culture media and mineral oils were not among the top MEA-failure frequencies, as only 48/1182 (4.1%) and 23/1907 (1.2%) toxic lot samples were registered for each category, respectively, both categories showed a nearly-extreme lethality caused by their toxic-assessed samples, reflected in 31.7 and 35.1% mean EBFRs. Limitations, reasons for caution Increasing the number of sample-providing manufacturers per category might strengthen the wider market representativeness of the results. Moreover, it should be noted that the identification of specific sources of toxicity results highly difficult, hindering the implantation of corrector modifications within the manufacturing process. Wider implications of the findings These findings indicate that protein supplements, flexipet-pipette types, steripettes, catheters and needles exhibit a heightened toxicity tendency. Additionally, toxic mineral oils and culture media-linked high-embryotoxicity levels were observed. Therefore, special attention should be given to the production of these demonstrated potentially embryotoxic products to identify and mitigate clinical toxicity risks. Trial registration number Not applicable

Economic perspectives in pharmaceuticals: market dynamics and pricing of medications

Background: Analysing the modern pharmaceutical market is crucial for making management decisions, forming strategies, and ensuring competitiveness in this sector. Aim: Determination of the impact of various economic factors of the pharmaceutical industry on market conditions and development of economically justified areas of cost formation in the pharmaceutical market. Materials and Methods: A systematic review of scientific publications in the search databases Scopus, Web of Science, Medline, and Google Scholar was conducted. Statistical research methods used are observation, index and regression analysis. The methods of benchmarking analysis and interpretation were applied. Results: A detailed examination of published works by scientists and doctors has highlighted critical problems in forming the cost of medicinal products in the pharmaceutical market. The use of medicines worldwide and in individual countries has been considered, and a trend of increasing revenue in the global pharmaceutical market has been identified. The main approaches to forming pricing models in the pharmaceutical industry have been summarised. The peculiarities of the formation of EU legislation on the registration, production, sale, and quality control of medicinal products have been highlighted. The characteristics of the functioning of reimbursement programmes in certain countries worldwide have been described. A benchmarking analysis of the pharmaceutical market economy in Ukraine and the European Union has been conducted. Conclusions: The main directions for improving pricing policy in the modern pharmaceutical market have been outlined. It has been established that the main directions for forming the cost of medicinal products are expenses on research and development, costs of goods sold and patent expenses, marketing and advertising, regulatory and permitting procedures, and market competition.

A comprehensive study of Tianma Toutong Tablets from the dual dimensions of quality and efficacy using fingerprint techniques and network pharmacology

BackgroundThe quality of traditional Chinese medicine (TCM) is the prerequisite for ensuring its safe and effective clinical application. With the increasing popularity of TCM worldwide, the quality control of TCM products has become increasingly crucial. Tianma toutong tablet (TMTTT) is mainly used for migraine caused by external wind and cold, blood stasis, or deficiency of blood and nourishment. However, the mechanism of action of TMTTT is still unclear, and there has been a lack of in vitro antioxidant activity research and migraine treatment mechanism research. Therefore, it is urgent to establish a set of comprehensive and effective evaluation methods. Resultsthree fingerprint profiles were established using HPLC, UV, and DSC analysis methods, and established three digital parameters simple complexity index (SX), simple clarity index (SY), simple complexity clarity ratio (Sω), 22 batches of samples were evaluated using a comprehensive linear quantitative fingerprint method (CLQFM). In addition, the antioxidant activity of the samples was determined using the DPPH method, and the relationship between fingerprint peaks in different fingerprints and antioxidant capacity was explored using Pearson correlation coefficients. Finally, network pharmacological research was conducted to investigate the potential targets, compounds, and pathways involved in the treatment of migraines with TMTTT. The results showed that the 22 batches of samples were classified into different quality grades. TMTTT exhibited good antioxidant activity, the fingerprint-efficacy relationship showed that gastrodin, chlorogenic acid, ferulic acid, imperatorin and isoimperatorin had strong antioxidant capacity, providing directions for the identification of active compounds. A total of 36 core targets were identified and screened by network pharmacology, which AKT serine/threonine kinase 1 (AKT1), albumin (ALB), insulin (INS), tumor necrosis factor (TNF), prostaglandin-endoperoxide synthase 2 (PTGS2) and interleukin-6 (IL-6), and compounds such as β-sitosterol, chrysophanol, vanillin are the key to the treatment of migraine, providing references for subsequent clinical research and new drug development. Significance: This study examined the consistency of the quality of TMTTT and the mechanism of action in treating migraines from both quality and efficacy perspectives, providing a favorable direction for further research on TMTTT and offering new ideas for the quality control of TCM compound formulations.

Functionality-type and chemical-composition separation of poly(lactide-co-glycolide) using gradient elution normal-phase liquid chromatography with basic and acidic additives

End groups of poly(Lactide-co-glycolide) (PLGA) play an important role in determining the properties of polymers for use in drug delivery systems. For instance, it has been reported that the encapsulation efficiency in PLGA microspheres varies significantly between ester-terminated and acid-terminated PLGA. More importantly, the in-vivo degradation time of such polymer excipients is influenced by the functional end-group of the copolymer used.The end group distribution in PLGA polymers has been studied using electrospray and matrix-assisted laser-desorption/ionization – high-resolution mass spectrometry. In both cases, the application of these methods is typically limited to PLGA having a molecular weight of up to 4 kDa. 13Carbon-nuclear-magnetic-resonance has also been reported as a method to differentiate and quantify PLGA end groups with a molecular weight up to 136 kDa. However, reported NMR methods take over 12 h per sample, limiting throughput.Cryoprobe NMR can reduce the time required for the process, however such NMR equipment is costly, which makes it unsuitable for the quality control of PLGA.Here, we present a normal-phase liquid chromatography method capable of resolving functionality type distribution (FTD) and, partially, chemical composition distribution (CCD) in commercial PLGA polymers obtained from ring opening polymerization. This method can separate PLGA polymers with a molecular weight of up to 183.0 kDa while also enabling the simultaneous separation of the difference of Lactic acid (LA)/Glycolic acid (GA) ratios.To achieve this, a cross-linked diol column was used with a ternary gradient from HEX to 0.1 % v/v TEA in EA to 0.1 % v/v FA in THF to allow first for the elution of mono-ester terminated PLGA, followed by the di-acid terminated. In addition, a separation of ester-terminated PLGA in the difference of the LA/GA ratio was achieved.This method is expected to aid in understanding the correlation between PLGA's FTD, CCD, and physical properties, facilitating product development and quality control.

In vitro CAR-T cell killing: validation of the potency assay

For advanced therapy medicinal products, the development and validation of potency assays are required, in accordance with international guidelines, to characterise the product and obtain reliable and consistent data. Our purpose was to validate the killing assay for the evaluation of autologous anti-CD19 chimeric antigen receptor (CAR) T potency. We used CD4 + and CD8 + lymphocytes or anti-CD19 CAR-T cells as effector cells and REH (CD19 +) or MOLM-13 (CD19 −) cell lines as target cells. After co-culturing target and effector cells (1:1 ratio) for 24 h, samples were labelled with 7-AAD, anti-CD3 and anti-CD19 antibodies and the frequency of CD19 + dead cells was evaluated by flow cytometry. In order to verify the CAR-T specificity for the CD19 + target, the co-culture between CAR-T and REH or MOLM-13 at different effector-to-target ratios was scheduled. Moreover, not transduced CD4 + and CD8 + lymphocytes were tested in comparison with CAR-T from the same donor to demonstrate the assay specificity. Linearity and accuracy were evaluated, and established acceptance criteria were compiled for both parameters (r2 ≥ 0.97 for linearity and average relative error ≤ 10% for accuracy). Furthermore, the method was considered robust when performed between 23 and 25 h of co-culture, and the intra-assay, inter-assay and inter-day precision was obtained. Finally, in order to verify the inter-analyst precision, the test was executed by three different operators and the intra-class correlation coefficient was > 0.4 in both cases. In conclusion, we consider this CAR-T potency assay as validated and usable in all steps of product development and quality control.

Evaluation of a flow cytometry-based method for determination of T-lymphocyte subtypes for quality assessment of cell therapy products

Chimeric antigen receptor-T (CAR-T) cell therapy is currently the best-known type of immune effector cells therapy. For CAR T-cell therapy, the determination of CD3+ T cells is necessary for the quality control of fresh leukapheresis product as starting material. The aim was to validate analytical method for quantification of percentage and absolute count of T lymphocyte subtypes (CD3+, CD4+ and CD8+ cells) in fresh apheresis products using single-platform method on flow cytometer BD FACS Canto II. Validation study included determination of precision, trueness (bias), assessment of linearity, carryover, comparison of results obtained with two different protocols on flow cytometer for CD3+ cells determination and stability study. For between-run precision coefficients of variation (CVs) were <20%, as well as bias for all T-lymphocyte subtypes. For within-run precision, CVs were <10%, except for low CD8+ cell (percentage 10.51% and viable absolute count 12.37%). Comparison of results obtained with two different protocols for CD3+ cells determination shows no statistically significant difference. Statistically significant differences between results of the analysis of CD4+ cells in fresh samples and results obtained after storage at 4 °C (p = .004) and at room temperature (p = .018) were found. In conclusion, method for enumeration of T-lymphocyte subtypes can be used in routine work on BD FACS Canto II instrument for quality assessment of fresh cell products collected by leukapheresis procedure.

Application scenario design and prospect of generative artificial intelligence (AI) in intelligent manufacturing and supply chain of traditional Chinese medicine

Intelligent manufacturing technologies, including databases, mathematical modeling, and information systems have played a significant role in process control, production management, and supply chain management in traditional Chinese medicine(TCM) industry. However, their ability to process and utilize unstructured data, such as research and development reports, batch production records, quality inspection records, and supplier documents, is relatively weak. For text, images, language, and other unstructured data, generative artificial intelligence(AI) technology has shown strong potential for development in extracting information, extracting knowledge, semantic retrieval, and content generation. Generative AI is expected to provide a feasible set of tools for the utilization of unstructured data resources in the TCM industry. Based on years of research and industrial application experience in TCM intelligent manufacturing technology, this study reviewed the current situation of intelligent manufacturing in TCM and the utilization of unstructured data, analyzed the application value of generative AI in the TCM manufacturing process and supply chain, summarized four typical application scenarios, including intelligent pharmaceutical knowledge base/knowledge graph, intelligent on-the-job trai-ning, intelligent production quality control, and intelligent supply chain. Furthermore, this study also explained the data collection and processing, business process design, application potential, and value of each scenario based on industry demands. Finally, based on the integration of generative AI and TCM industrial models, the study proposed a preliminary concept of a smart industrial brain for TCM, aiming to provide a reference for the application of AI technology in the field of TCM manufacturing.

Quality control of garment product using DMAIC Six Sigma

Quality control is intended to ensure that the products are in accordance with the predefined standards. PT. XYZ is a garment company that manufactures products with global target market. Hence, product quality assurance becomes an important issue for PT. XYZ. This research focuses on the Just Brand-MCJA216142 jacket product at the sewing work station on line-4 of PT. XYZ. Preliminary observations show that the number of reworked-products was experiencing an increasing trend. This study aims to determine whether the company has carried out quality control properly. Specifically, the research objectives are to identify the type and level of product defects, identify the factors causing product defects, and provide proper improvement suggestions to reduce the occurrence of product defects. This study applied DMAIC (Define–Measure–Analyze–Improve–Control) Six Sigma concept. The results showed that the quality of the Just Brand-MCJA216142 jacket product has exceeded the Indonesian industry average and is classified as the USA industry average. However, quality improvement is still needed since the products are targeted for the export market. Based on Pareto diagram at the Analyze stage, it was found that the most dominant defects occurred in the Just Brand-MCJA216142 jacket production process were broken threads and puckering. The frequency of occurrence for these two types of defect reaches 23% of the total 16 types of defects. The defects were caused by human, machine, material, method, and environmental factors. Recommendations for improvement at the Improve stage are based on root cause analysis of each causative factor that is identified using a fishbone diagram. This research results strengthen the previous related researches regarding the effectivity of DMAIC Six Sigma for analyzing quality control of products.

Development of Automated Physical Defect Inspection Systems in Greige Tarpaulin Fabric Based on Machine Learning Algorithms

The textile industries in Indonesia have challenges, one of which is improving the efficiency of processes. PT NTX is a weaving industry company that produces gray tarpaulin textile products. In this industry, the inspection process for gray cloth resulting from the weaving process is generally carried out conventionally, using a cloth inspection machine and visually with the human eye. Traditional inspection methods cannot be applied to greige tarpaulin textile products since the characteristics of the greige tarpaulin textile are very prone to shifting or slipping of the woven thread construction if it is pulled, touched, or rewound. The process of detecting defects and quality control of greige tarpaulin textile products is carried out by the operator on the loom during the weaving process. This process, of course, will result in the need for inspection operators with high skills, and the consistency of inspection results is very dependent on the condition of the inspection operator. This research has used image processing techniques based on machine learning algorithms to overcome this problem by examining the product directly on the machine. This research has used the Mean Pixel Value method combined with the Logistic Regression Model and the Local Binary Pattern method combined with the Support Vector Machine as image process techniques. Based on the research results, the Mean Pixel Value method combined with the Logistic Regression Model had an accuracy rate of 61% on greige tarpaulin images, and the Local Binary Pattern method with the Support Vector Machine had an accuracy rate of 68%.

Enhancing Quality Control in Bottled Water Production

Enhancing Quality Control in Bottled Water Production

Quality Control of Kinasih Bread Products Using Statistical Quality Control and Failure Mode and Effect Analysis Methods

Roti Kinasih UMKM is a business that focuses on the culinary sector by producing various types of bread. The business process carried out at this UMKM is a Make to Order system where products are made after receiving orders from customers. One problem that often arises is the inability to control product quality. Having defective products has a big impact on MSMEs because the costs incurred increase. Based on the existing problems, the Statistical Quality Control and Failure Mode And Effect Analysis methods were chosen to determine the factors causing product defects in UMKM Roti Kinasih. The aim of this research is to determine the level of defects in Kinasih bread products and carry out quality control measures using statistical methods. After processing and analyzing the data, it was found that the burnt bread defect and the sinking bread defect were said to be in an uncontrolled condition and needed recommendations for improvement. The highest RPN value for the burnt bread defect was 245 with the overtime baking failure mode, while the RPN value for the sinking bread defect was 175 with the too cold room temperature failure mode.

Application of AI-based welding process monitoring for quality control in pipe production

Application of AI-based welding process monitoring for quality control in pipe production

DECISION-MAKING SUPPORT TECHNOLOGIES IN THE FORMATION OF QUALITY MANAGEMENT SYSTEMS AT VEHICLE REPAIR ENTERPRISES

In recent years, the strategy of creating a safely functioning and efficient transport complex of Ukraine integrated into the world transport network has been fixed. Therefore, the creation of a progressive system of product quality management in the conditions of car repair enterprises is considered an urgent scientific and technical task. The quality management system is a management subsystem of an industrial enterprise. Modern production systems are based on TQM principles and widely use ISO 9001 certification. At the same time, certification is based on independent third-party audits (a conformity assessment organization). The wide spread of the standard is based on the fact that it contains generalized requirements (principles) for the organization of product quality control, which can be used at enterprises that differ significantly both in terms of specialization and the scale of production (depots or car repair plants). But this is the «bottleneck» of the standard – the lack of consideration of specialized production conditions makes it impossible to compensate for critical factors affecting the final quality of products. Currently, the accepted approaches to quality assessment do not fully take into account the factors that affect the final quality of products. In order to put all market participants - railway operators, manufacturers, rolling stock repairers and suppliers in mutually beneficial conditions, a single International Railway Industry Standard ISO / TS 22163 International Railway Industry Standart (IRIS) was developed.For the effective use of tools for ensuring the quality of rail car repair, it is considered necessary to use modern management decision support systems. They will allow real-time monitoring of production processes. It is possible to use the method of fuzzy sets to improve the quality management systems of wagon repairs based on the development of separate control algorithms with decision tables. In order to meet the requirements of international quality standards, it is necessary to significantly modernize management approaches based on the creation of progressive decision support systems.