Quality Control Approach Research Articles

A Fault Detection Robotic Cell Application Based on Deep Learning and Image Processing Hybrid Approach for Quality Control of Automotive Parts

A Fault Detection Robotic Cell Application Based on Deep Learning and Image Processing Hybrid Approach for Quality Control of Automotive Parts

Application of Quantitative Proton Nuclear Magnetic Resonance Spectroscopy for Determination of the Content of Geniposide in Gardeniae fructus

Background: Gardeniae fructus (Zhi-Zi) is the dry ripe fruit of the plant Gardenia jasminoides Ellis (Rubiaceae), which can be used as both food and medicine. Geniposide, a key constituent of Gardeniae fructus, serves as an indicator component for evaluating the quality of Gardeniae fructus. Traditionally, the quantification of geniposide in Gardeniae fructus is achieved through High-performance Liquid Chromatography (HPLC)-based methods. Objective: The present study aimed to introduce a rapid approach to quantifying geniposide content in Gardeniae fructus along with validating its effectiveness. Methods: The experiments involved finding a suitable deuterium solvent, Internal Standard (IS), specific peak, and Nuclear Magnetic Resonance (NMR) parameters for quantitation, and validating specificity, accuracy, precision, and stability. Results: The results have indicated that methanol-d4 as a solvent has facilitated excellent signal separation in the proton Nuclear Magnetic Resonance (1H NMR) spectroscopy, with trimethyl 1,3,5- benzenetricarboxylate emerging as the ideal IS. The specific signal at δ 7.45, corresponding to H-3 in geniposide, has been identified as the optimal peak for integration. The application of distinctive signals from the 1H NMR spectroscopy has allowed for the precise quantification of geniposide in Gardeniae fructus. Conclusion: This study has suggested using 1H NMR to quantify geniposide in Gardeniae fructus to be a viable alternative to HPLC-based methods, providing a suitable approach for quality control of Gardeniae fructus.

Greenness and Whiteness Assessed Mathematically Filtered UV Spectroscopic Approaches for Quality Control of Amlodipine, Telmisartan and Metoprolol from Ternary Formulation

Greenness and Whiteness Assessed Mathematically Filtered UV Spectroscopic Approaches for Quality Control of Amlodipine, Telmisartan and Metoprolol from Ternary Formulation

Acoustic insights into the corn extrusion process for enhanced quality control

In industrial extrusion processes, a solid material is pressed through a die to obtain products of the desired shape and dimension. Fluctuations in the process parameters have a significant impact on the product quality. In food extrusion, the expansion noise at the die can serve as an indicator of the stability of the process. This study employs microphones to characterize the corn extrusion process, focusing on correlating acoustic emissions with predefined process parameters such as feed intake and water content. Experimental data from laboratory and industrial settings reveal distinct domain shifts, yet consistent findings confirm the distinguishability of various extrusion process parameters by analyzing acoustic emissions. Employing machine learning models, including support vector machines and convolutional neural networks, in conjunction with audio features such as log Mel spectrograms, yields promising accuracies above 90\% in discriminating between standard and non-standard process parameters. The proposed acoustic quality control approach has the potential to enhance the stability of extrusion processes and contributes to the development of automated monitoring systems in the field of food extrusion. This ensures consistent quality and reduced waste, ultimately leading to significant cost savings in production.

Real-time automated quality control for quantitative MRI.

This work presents an automated quality control (QC) system within quantitative MRI (qMRI) workflows. By leveraging the ISMRM/NIST quantitative MRI system phantom, we establish an open-source pipeline for rapid, repeatable, and accurate validation and stability tracking of sequence quantification performance across diverse clinical settings. A microservice-based QC system for automated vial segmentation from quantitative maps was developed and tested across various MRF acquisition and protocol designs, with reports generated and returned to the scanner in real time. The system demonstrated consistent and repeatable value segmentation and reporting, successfully extracted all 252 T1 and T2 vial samples tested. Values extracted from the same sequence were found to be repeatable with 0.09% ± 1.23% and -0.26% ± 2.68% intersession error, respectively. By providing real-time quantification performance assessment, this easily deployable automated QC approach streamlines sequence validation and long-term performance monitoring, vital for the broader acceptance of qMRI as a standard component of clinical protocols.

Surface insight: Leveraging high-density dataset fusion for enhanced roughness classification

The ability to assess the surface quality quickly and accurately is of immense importance in manufacturing system. Modern metrology system along with machine learning is great at classification but requires more time. Traditionally accessing surface roughness is a time-consuming process. The progress in manufacturing technology necessitates improved approaches for quality control, specifically in the categorization of surface roughness, which has a substantial impact on the performance of materials. This research study introduces a novel method for classifying surface roughness by combining image data and point cloud data to create a comprehensive model. It then compares the performance of this model with a model that just relies on image data. A comprehensive analysis is conducted in this study, where image and point cloud data is collected and analysed. Multilinear principal component analysis (MPCA) along with random forest classifier is employed to create a model that classifies the surface texture. The primary goal is to showcase the enhanced precision and comprehensive understanding offered by the fused data model compared to the model that solely relies on images.Furthermore, the work presents a pragmatic approach for developing this enhanced model offline and applying it online in real-time production environments, with a particular focus on using only image data. This strategy is in line with the objectives of Industry 4.0, which seeks to achieve more intelligent and data-driven manufacturing processes. Subsequent investigations will prioritize expanding the model’s suitability to various manufacturing settings, particularly highlighting its capacity to ensure quality in manufacturing lines through the utilization of images.

A Comprehensive Analytical Approach for Quality Control of Collagen in Food Supplements.

Collagen is a popular nutricosmetic ingredient in food supplements due to its anti-aging and other positive effects on the skin. Due to its widespread use and the lack of regulation in this area, appropriate quality control is required to ensure efficacy and safety, with the development of analytical methods playing an important role. Currently, the quantitative determination of collagen is mainly based on time-consuming derivatization-based spectroscopic methods or on complex chromatographic methods with mass spectrometric detection. Therefore, in this study, two new, simple chromatographic methods have been developed. One is intended for the analysis of untreated samples and is characterized by the speed and simplicity of sample preparation. The other method quantifies collagen via the underivatized tripeptide Gly-Pro-Hyp formed by bacterial collagenase hydrolysis and is characterized by its specificity and ability to distinguish between marine and terrestrial collagen. The latter is a novelty in the field of simple methods for collagen analysis and is particularly important in terms of safety. Our comparison with established analytical methods (e.g., via hydroxyproline after complete hydrolysis) for collagen analysis undoubtedly showed the superiority of these new methods for the routine quality control of collagen supplements in terms of specificity, repeatability, sample stability, and simplification in sample preparation. The collagen content in the supplements tested was found to be adequate; however, some discrepancies were found regarding the labeling and origin of the collagen, with possible safety implications.

Anti-aging based on stem cell therapy: A scoping review.

Stem cells are present in the tissues and organs and remain in a quiescent and undifferentiated state until it is physiologically necessary to produce new descendant cells. Due to their multipotency property, mesenchymal stem cells have attracted considerable attention worldwide due to their immunomodulation and therapeutic function in tissue regeneration. Stem cells secrete components such as paracrine factors, extracellular vesicles, and exosomes which have been shown to have anti-inflammatory, anti-aging, reconstruction and wound healing potentials in many in vitro and in vivo models. The pluripotency and immunomodulatory features of stem cells could potentially be an effective tool in cell therapy and tissue repair. Aging affects the capacity for self-renewal and differentiation of stem cells, decreasing the potential for regeneration and the loss of optimal functions in organisms over time. Current progress in the field of cellular therapy and regenerative medicine has facilitated the evolution of particular guidelines and quality control approaches, which eventually lead to clinical trials. Cell therapy could potentially be one of the most promising therapies to control aging due to the fact that single stem cell transplantation can regenerate or substitute the injured tissue. To understand the involvement of stem cells not only in tissue maintenance and disease but also in the control of aging it is important to know and identify their properties, functions, and regulation in vivo, which are addressed in this review.

Rapid identification of moxa wool storage period based on hyperspectral imaging technology and machine learning

Moxa wool (MW), derived from the dried leaves of Artemisiaargyi, plays a significant role in traditional Chinese medicine. However, the quality of MW varies with its storage period, impacting its therapeutic efficacy. Traditional methods for quality detection are limited and destructive. To address this, we propose a non-destructive detection method using hyperspectral imaging technology and machine learning algorithms to accurately identify the storage period of MW. Nevertheless, hyperspectral data poses challenges due to its high dimensionality and redundancy, leading to increased computational complexity. To overcome this, we employed principal component analysis (PCA), competitive adaptive reweighted sampling (CARS), and successive projection algorithm (SPA) for data dimensionality reduction and wavelength selection. The results demonstrate that these techniques significantly enhance the accuracy of MW storage year identification. For Nanyang MW, the CARS+SVM model achieved the highest accuracy rates of 99.8% in the visible-near-infrared (VNIR) range and 99.55% in the shortwave infrared (SWIR) range. Similarly, for Qichun MW, the SPA+SVM model achieved identification accuracies of 99.78% and 99.47% in the VNIR and SWIR ranges, respectively. This research provides valuable insights into the rapid detection of MW quality by indication of storage years and presents a novel approach for quality control of MW in the field of traditional Chinese medicine. The combination of hyperspectral imaging and machine learning offers a promising solution for efficient and accurate MW identification, contributing to the advancement of traditional medicine practices.

A hierarchical multi-parametric programming approach for dynamic risk-based model predictive quality control

In this work, we present a hierarchical batch quality control strategy with real-time process safety management. It features a multi-time-scale decision-making framework augmenting: (i) Risk-aware model predictive controller for short-term set point tracking and dynamic risk control under disturbances; (ii) Control-aware optimizer for long-term quality and safety optimization over the entire batch operation; (iii) Intermediate surrogate model to bridge the timescale gap by readjusting the optimizer operating decisions for the controller. All of the above problems are solved via multi-parametric mixed-integer quadratic programming with a key advantage to generate offline explicit control/optimization laws as affine functions of process and risk variables. This allows for the design of a fit-for-purpose risk management plan prior to real-time implementation, while reducing the need for repetitive online dynamic optimization. A unified process model is used to underpin the consistency of hierarchical operational optimization. The proposed approach offers a flexible strategy to integrate distinct decision-making time scales which can be selected separately tailored to the process-specific need of control, fault prognosis, and end-batch quality control. A T2 batch reactor case study is presented to showcase this approach to systematically address the interactions and trade-offs of multiple decision layers toward improving process efficiency and safety.

A novel evaluation mode of Nao An Capsules using multi-wavelength fusion fingerprint combined with quantitative analysis of multi-components by a single marker method and antioxidant activity

Nao An Capsules (NAC) are utilized in the acute phase of cerebral thrombosis and are appropriate for patients in the recovery stage exhibiting symptoms of qi deficiency and blood stasis. Nevertheless, there has been a lack of recent research on the overall quality control of NAC. The objective of this study is to establish a comprehensive quality control strategy for NAC. This article presents a methodology based on the average linear quantitative fingerprinting method (ALQFM) in conjunction with multi-wavelength high performance liquid chromatography (HPLC) fusion fingerprinting, quantized Fourier transform infrared (FT-IR) spectroscopy and ultraviolet (UV) spectral techniques to comprehensively evaluate NAC from both qualitative and quantitative perspectives. Subsequently, quantitative analysis of multi-components by a single marker (QAMS) method and the Standard Curve Method (SCM) were used to quantitatively determine 10 quality markers (Q-markers) in 22 batches of samples, with the results indicating that QAMS is a reliable method for quantifying active ingredients. Chemometrics methods such as principal component analysis (PCA) and principal component analysis (HCA) were also used to analyze the quality of samples. To achieve a thorough and methodical evaluation, a combined assessment of the three fingerprints was executed. Subsequently, an in vitro antioxidant activity experiment was performed utilizing the 1,1-diphenyl-2-picrylhydrazyl (DPPH) radical-scavenging technique. By employing a partial least squares (PLS) model, the correlation between HPLC fingerprint chromatography and antioxidant activity was investigated. The study found that out of the 59 common peaks in the five-wavelength fusion fingerprint spectra of NAC, 33 peaks exhibit antioxidant activity. In this study, multi-wavelength fusion HPLC, quantized FT-IR and UV were jointly used to effectively identify functional groups and fingerprint information in compounds. It can fully and quickly obtain the fingerprint information of the compounds in the sample. NAC multi-components quantification and overall quality evaluation were performed using ALQFM and QAMS and chemometrics methods. We have developed a new approach for comprehensive, rapid, and cost-effective quality control of traditional Chinese medicine (TCM) compound preparations.

Power modulation spectrum – a promising approach for the indispensable quality control of electrocardiogram signals from monitoring units for the detection of autonomic dysfunction

ObjectiveElectrocardiogram (ECG) is essential for evaluating the autonomic nervous system. Ensuring the quality of real-world ECG datasets is critical, but manual control of large datasets is impractical. Thus, automated quality control is necessary. This paper introduces a new quality index, the peak-distance quality index (PDQI), based on the modulation spectrum approach. MethodsReal-life data from 1000 ECG recordings, each 600 s long, were collected at the stroke unit of the University Hospital Tulln. Each ECG was visually evaluated, including the duration of the signal, artefacts and noise, and the number of extrasystoles. The power-modulation spectrum, the percentage of ECG in each signal, and modulation spectrum-based quality index (MS-QI) and PDQI were calculated. The area under the curve (AUC) for the detection of high-quality ECGs was calculated for both quality indices, as well as the optimal threshold for each index. ResultsThe percentage of ECG signals in the recordings based on the modulation spectrum correlates with expert rating (r = 0.99, p < 0.001). The AUC for PDQI for the detection of extrasystoles is 0.96, and the AUC for MSQI for the detection of artefacts is 0.83. The optimal thresholds for PDQI and MSQI are 0.44 and 0.17, respectively ConclusionThe power modulation spectrum can be applied to large amounts of data to detect ECG signals within biosignals and calculate quality indices. MSQI can be used for artefact detection and PDQI for extrasystole detection in ECG signals. A combined approach using both quality indices can provide a picture of the underlying data quality.

DeepQC: A deep learning system for automatic quality control of in-situ soil moisture sensor time series data

Amidst changing climate, real-time soil moisture monitoring is vital for the development of in-season decision support tools to help farmers manage weather-related risks in agriculture. Precision Sustainable Agriculture (PSA) recently established a real-time soil moisture monitoring network across the central, Midwest, and eastern U.S., but continuous field-scale sensor observations often come with data gaps and anomalies. To maintain the data quality and continuity needed for developing decision tools, a quality control system is necessary.The International Soil Moisture Network (ISMN) introduced the Flagit module for anomaly detection in soil moisture time series observations. However, under certain conditions, Flagit's threshold and spectral based quality control approaches may underperform in identifying anomalies. Recently, deep learning methods have been successfully applied to detect time series anomalies in time series data in various disciplines. However, their use in agriculture for anomaly detection in time series datasets has not been yet investigated. This study focuses on developing a Bi-directional Long Short-Term Memory (LSTM) model, referred to as DeepQC, to identify anomalies in soil moisture time series data. Manual flagged PSA observations were used for training, validation, and testing the model, following an 80:10:10 split. The study then compared the DeepQC and Flagit-based estimates to assess their relative performance.Flagit correctly flagged 95.8 % of the correct observations and 50.3 % of the anomaly observations, indicating its limitations in identifying anomalies, particularly at sites consists of more than 30 % anomalies. On the other hand, the DeepQC correctly flagged 89.8 % of the correct observations and 99.5 % of the anomalies, with overall accuracy of 95.6 %, in significantly less time, demonstrating its superiority over Flagit approach. Importantly, the performance of the DeepQC remained consistent regardless of the number of anomalies in site observations. Given the promising results obtained with the DeepQC, future studies will focus on implementing and finetuning this model on national and global soil moisture networks.

Comprehensive identification of key quality markers of Buzhong Yiqi Oral Liquid based on multi-dimensional characteristic networks

Traditional Chinese Medicine (TCM) formulations often contain a complex mixture of compounds, making it challenging to evaluate their quality. Buzhong Yiqi Oral Liquid (BYOL), a well-known TCM formulation, has been used to treat gastrointestinal diseases and fatigue for a long time. However, the effective substances for its therapeutic effects remain unclear. This study aimed to establish a novel quality control approach for BYOL using a multidimensional feature network to identify quality markers (Q-markers). The multidimensional characteristic network was constructed by a “Spider-Web” model, including the compatibility of ingredients, traceability of compounds from raw materials to the final product, effectiveness, measurability, and stability. Multivariate statistical analysis was applied to quantify the individual dimensions of the feature network, and candidate compounds were identified based on regression regions within the network. Using the multidimensional characteristic network, 12 components were identified as key Q-markers for BYOL, consisting of calycosin-7-O-β-D-glucoside, formononetin, astragaloside IV, liquiritin, quercetin, hesperidin, glycyrrhizic acid, isorhamnetin, liquiritin apioside, hesperidin, luteolin, and nobiletin. The identified Q-markers offered valuable insights for future research on medicinal substances and quality control of BYOL.

A new paradigm in cigarette smoke detection: Rapid identification technique based on ATR-FTIR spectroscopy and GhostNet-[formula omitted]

In the tobacco field, the analysis and classification of cigarette smoke are crucial for ensuring product quality, protecting consumer health, and driving industry innovation. These analyses provide a comprehensive understanding of tobacco products and serve as a scientific basis for production standards and regulatory policies. Traditional infrared spectroscopy techniques for tobacco quality analysis often suffer from limitations such as time consumption, high costs, and complexity. To achieve efficient detection of cigarette smoke and quality control of cigarettes, this study developed a cigarette mainstream smoke detection system based on Attenuated Total Reflectance Fourier transform infrared (ATR-FTIR) spectroscopy technology, aimed at rapidly acquiring the mid-infrared (MIR) spectral characteristics of cigarette smoke and combining deep learning for rapid cigarette type identification. Five different brands of cigarettes were selected for this study, and a total of 400 MIR spectra of cigarette smoke aerosols were collected. Using three spectral preprocessing methods and two-dimensional correlation spectroscopy (2DCOS), we extracted the fingerprint region (1850–650 cm-1) to generate 4800 2DCOS images. We then optimized the GhostNet network architecture and constructed a more compact and efficient deep learning model, GhostNet-α. A mixed-precision training strategy further enhanced model training speed and computational efficiency. Results show that Multiple Scatter Correction (MSC)-preprocessed synchronous 2DCOS images achieved 100 % classification accuracy. This study validates GhostNet-α’s efficiency and accuracy in cigarette smoke recognition, offering a new technical approach for quality control and rapid detection in the tobacco industry, significantly enhancing its competitiveness and consumer health protection.

A Cost-effective approach for quality control in PLA-based material extrusion 3D printing using 3D scanning

In this article, our aim is to underscore the importance of verifying that components produced through material extrusion additive manufacturing exhibit geometric and dimensional conformity with the STL (Standard Tessellation Language) model. Currently, the business world is heavily investing in additive technologies, but it is crucial to obtain feedback on the accuracy of the printed component without excessive economic expenditure. For this reason, we have opted to utilize a mid-range 3D scanner (Revopoint Mini with an accuracy of 0.02 mm) to investigate any disparities in print results using PLA material. Each model has been scanned and compared with the initial mesh to qualitatively and quantitatively assess the present errors. The analysis has revealed that the majority of features can be effectively controlled, while the remaining ones either fall within the tool's precision or necessitate a higher-quality scan. Particularly in the analysed case, flat surfaces, profiles of complex geometries, and holes have demonstrated dimensional and geometric controllability. However, details of reduced dimensions or those difficult to reach by the scanner do not allow for adequate comparison due to excessive standard deviation in the error. The analysed layer heights do not exhibit a significant impact on component accuracy.

Development of a Predictive Model for the Thermal Conductivity of Natural Fiber Insulation: A Novel Approach for Quality Control

ABSTRACT Natural fiber insulation materials can offer a sustainable alternative to mineral and petrochemical-based insulation materials when suitable raw materials and appropriate production processes are considered. Within the scope of our research, natural fibers like cotton, flax, hemp, wool, and coir, as well as regenerated cellulose fiber, were processed into insulation materials and examined concerning their thermal conductivity. We demonstrate that simple test methods for fiber fineness measurement with air-flow methods such as Airflow and Shirley can facilitate incoming inspection and process monitoring for insulation manufacturers. Based on these measurements, a simple model was developed to estimate the thermal conductivity based on the fineness measurements of the raw materials. The model developed on the natural fibers for lower densities was tested on a glass fiber insulation material to check its suitability. The slight deviations achieved between the experiment and the calculation verify the practicability of the concept.

Photogrammetry-Based Method for Measuring Volume Changes of Soil Specimens During Critical Phases of Triaxial Testing

Triaxial tests has been routinely used to measure the stress–strain relationship for geomaterials. During triaxial testing, many sources of errors that cannot be completely avoided but are often ignored or approximated using empirical equations. This paper presents a systematic investigation of soil volume change, volume strain nonuniformity, and cross-sectional calculation along the specimen during triaxial testing using a photogrammetry-based method. Consolidated drained triaxial tests were performed in which two parallel measurements were taken: (1) relative volume using the conventional triaxial testing and (2) absolute volume using the photogrammetry-based method. The difference in the observed volume and void ratio measurements between the two methods highlighted the importance of absolute soil volume over the relative volume method. The results revealed the effect of soil volume change in the interpretation of triaxial testing findings. Various preparation steps and procedures during triaxial testing have influenced the initial measured volume and thus caused deviation of the subsequent associated measurements. This method would present a quality control approach for different aspects of triaxial testing to improve the test simulations to accurately measure the soil behavior. The proposed method is important for more refined simulations and identification of setup-induced errors. Additional applications of the current research would allow correct determination of the stress path followed during triaxial testing, the critical-state soil mechanics parameters, and the stress–strain relationship, including deformation and strength parameters.

A Novel Online Hydrological Data Quality Control Approach Based on Adaptive Differential Evolution

The quality of hydrological data has a significant impact on hydrological models, where stable and anomaly-free hydrological time series typically yield more valuable patterns. In this paper, we conduct data analysis and propose an online hydrological data quality control method based on an adaptive differential evolution algorithm according to the characteristics of hydrological data. Taking into account the characteristics of continuity, periodicity, and seasonality, we develop a Periodic Temporal Long Short-Term Memory (PT-LSTM) predictive control model. Building upon the real-time nature of the data, we apply the Adaptive Differential Evolution algorithm to optimize PT-LSTM, creating an Online Composite Predictive Control Model (OCPT-LSTM) that provides confidence intervals and recommended values for control and replacement. The experimental results demonstrate that the proposed data quality control method effectively manages data quality; detects data anomalies; provides suggested values; reduces reliance on manual intervention; provides a solid data foundation for hydrological data analysis work; and helps hydrological personnel in water resource scheduling, flood control, and other related tasks. Meanwhile, the proposed method can also be applied to the analysis of time series data in other industries.

SpotSweeper: spatially-aware quality control for spatial transcriptomics.

Quality control (QC) is a crucial step to ensure the reliability and accuracy of the data obtained from RNA sequencing experiments, including spatially-resolved transcriptomics (SRT). Existing QC approaches for SRT that have been adopted from single-nucleus RNA sequencing (snRNA-seq) methods are confounded by spatial biology and are inappropriate for SRT data. In addition, no methods currently exist for identifying histological tissue artifacts unique to SRT. Here, we introduce SpotSweeper, spatially-aware QC methods for identifying local outliers and regional artifacts in SRT. SpotSweeper evaluates the quality of individual spots relative to their local neighborhood, thus minimizing bias due to biological heterogeneity, and uses multiscale methods to detect regional artifacts. Using SpotSweeper on publicly available data, we identified a consistent set of Visium barcodes/spots as systematically low quality and demonstrate that SpotSweeper accurately identifies two distinct types of regional artifacts, resulting in improved downstream clustering and marker gene detection for spatial domains.