Quality Improvement Techniques Research Articles

Evaluation and Application of Machine Learning Techniques for Quality Improvement in Metal Product Manufacturing

This article presents a discussion of the application of machine learning methods to enhance the quality of drive shaft production, with a particular focus on the identification of critical quality issues, including cracks, scratches, and dimensional deviations, which have been observed in the final stages of machining. A variety of classification algorithms, including neural networks (NNs), bagged trees (BT), and support vector machines (SVMs), were employed to efficiently analyse and predict defects. The results show that neural networks achieved the highest accuracy (94.7%) and the fastest prediction time, thereby underscoring their efficiency in processing complex production data. The BT model demonstrated stability in its predictions with a slower prediction time, while the SVM model exhibited superior training speed, though with slightly lower accuracy. This article proposes that optimising key process parameters, such as temperature, machining speed, and the type of coolant used, can markedly reduce the prevalence of production defects. It also recommends integrating machine learning with traditional quality management techniques to create a more flexible and adaptive control system, which could help reduce production losses and enhance customer satisfaction.

Sound quality improvement technique for inverter-driven motors

Motor-driven products are becoming increasingly popular along with the trend toward carbon neutrality. Motor units driven by PMW inverters are one of the key components of motor-driven products, but since they are also one of the dominant sound sources, there are high demands for quietness, including sound quality improvement, in terms of comfort. During the DC-AC conversion process, the PWM inverter generates harmonic current distortions and, moreover, the electromagnetic excitation forces generated in the air gap between the rotor and stator induce harmonic vibrations in the motor. Therefore, this presentation describes the mechanism of motor noise generation from the excitation source to propagation and radiation, and activities to improve sound quality for the motor unit driven by inverters.

Application of Artificial Intelligent Techniques for Power Quality Improvement in Microgrid System

This paper focuses on modeling, control and power quality improvement of a microgrid connected system. This last was designed as a multi-converter system with Wind Turbine driven Permanent Magnet Synchronous Generator, and lithium ion Battery Storage Energy System. These sources are connected by a continuous bus to a nonlinear load through a DC /AC converter and three-phases multi-functional voltage source inverter. Where, wind systems are considered as primary power resource, and the grid is used for the effect of consumption of the overage power available from sources, when the battery has been fully charged. Multi Functional Voltage Source Inverter is used to ameliorate the performance of the proposed system, guaranteeing both reactive power and harmonic compensation. Moreover an intelligent control by fuzzy logic control algorithm are managed In order to extract the maximum power from wind turbine, to guarantee an effective storage management, this about the DC side. For the AC side a direct power control strategy with fuzzy logic algorithm have been used. The simulation of the system solution is carried out in Matlab/Simulink. The obtained simulation results show that the technique of fuzzy logic furnish the best solution in term of robustness, optimization performance, low THD and fast dynamic response.

Improving genetic testing utilization in a tertiary care neonatal intensive care unit through quality improvement.

There is an increasing recognition of the importance of diagnosing genetic conditions with an ever-growing list of genetic testing options. However, most providers do not have formal genetics training, which makes choosing the most appropriate test to order challenging. Our project sought to improve cytogenetic testing utilization in a tertiary care neonatal intensive care unit (NICU) through utilizing quality improvement techniques, specifically the Model for Improvement framework with rapid Plan-Do-Study-Act cycles. Our project utilized various interventions including the implementation of a NICU genetic testing algorithm. Interventions demonstrated improvement in all areas, specifically a 92% reduction in unnecessary cytogenetic testing with improvement in the diagnostic rate. Our work also resulted in a 59% decrease in charges with an estimated projected savings of $21,000 per year. Quality improvement can minimize redundancies and inefficiencies in genetic testing in a Level IV NICU in a large tertiary care children's hospital and result in substantial cost-savings.

Using Shunt Capacitors to Mitigate the Effects of Increasing Renewable Energy Penetration

Over the past two decades, Renewable Energy Sources (RESs) have gained global popularity. Control issues are becoming more difficult as the system inertia decreases due to the absence of typical synchronous generators. Innovative methods like fault current limiters, energy storage devices, and alternative control systems are utilized to deal with these difficulties. This study provides a summary of the challenges associated with incorporating high-level RESs into the existing grid. The increased penetration of the RESs has a negative impact on the system oscillations and harmonics, generating the need for power quality improvement techniques, such as adaptive control, adding energy systems, power stream assessment, or weight stream examination. This paper presents a framework of the power stream issue, its arrangement as well as different game plan methods. The power stream model of a power structure can be built using the significant association, weight, and age data.

A Classification Method for Incomplete Mixed Data Using Imputation and Feature Selection

Data missing is a ubiquitous problem in real-world systems that adversely affects the performance of machine learning algorithms. Although many useful imputation methods are available to address this issue, they often fail to consider the information provided by both features and labels. As a result, the performance of these methods might be constrained. Furthermore, feature selection as a data quality improvement technique has been widely used and has demonstrated its efficiency. To overcome the limitation of imputation methods, we propose a novel algorithm that combines data imputation and feature selection to tackle classification problems for mixed data. Based on the mean and standard deviation of quantitative features and the selecting probabilities of unique values of categorical features, our algorithm constructs different imputation models for quantitative and categorical features. Particle swarm optimization is used to optimize the parameters of the imputation models and select feature subsets simultaneously. Additionally, we introduce a legacy learning mechanism to enhance the optimization capability of our method. To evaluate the performance of the proposed method, seven algorithms and twelve datasets are used for comparison. The results show that our algorithm outperforms other algorithms in terms of accuracy and F1 score and has reasonable time overhead.

Far-focus compound ultrasound imaging with lag-one coherence-based zero-cross factor.

Ultrasound imaging has been widely used in clinical examination because of portability, safety, and low cost. However, there are still some main challenges of imaging quality that remain in conventional ultrasound systems. Improving image quality of SA-based methods using an improved imaging mode named far-focus compound (FSC) imaging. A far-focus compound (FSC) imaging based on full-aperture transmission and full-aperture reception is proposed in this paper. In transmission, it uses the full aperture to transmit the focused beam to ensure image resolution and emission of sound field energy. In reception, the full aperture is used to receive the reflected beam to ensure the image quality. A lag-one coherence-based zero-cross factor (LOCZF) is then implemented in FSC for improvement of contrast ratio (CR). The LOCZF uses lag-one coherence as zero-cross factorâs adaptive coefficient. Comparisons were made with several other weighting techniques by performing simulations and experiments for performance evaluation. Results confirm that LOCZF applied to FSC offers a good image contrast and simultaneously the speckle pattern. For simulated cysts, CR improvement of LOCZF reaches 194.1%. For experimental cysts, CR improvement of LOCZF reaches 220%. From the in-vivo result, compared with FSC, CR improvement of LOCZF reaches 112.7%. Proved gCNR performance. In addition, the LOCZF method shows good performance in experiments. The proposed method can be used as an effective weighting technique for improvement of image quality in ultrasound imaging.

Factors Influencing Data Quality in Electronic Health Record Systems in 50 Health Facilities in Rwanda and the Role of Clinical Alerts: Cross-Sectional Observational Study.

Electronic health records (EHRs) play an increasingly important role in delivering HIV care in low- and middle-income countries. The data collected are used for direct clinical care, quality improvement, program monitoring, public health interventions, and research. Despite widespread EHR use for HIV care in African countries, challenges remain, especially in collecting high-quality data. We aimed to assess data completeness, accuracy, and timeliness compared to paper-based records, and factors influencing data quality in a large-scale EHR deployment in Rwanda. We randomly selected 50 health facilities (HFs) using OpenMRS, an EHR system that supports HIV care in Rwanda, and performed a data quality evaluation. All HFs were part of a larger randomized controlled trial, with 25 HFs receiving an enhanced EHR with clinical decision support systems. Trained data collectors visited the 50 HFs to collect 28 variables from the paper charts and the EHR system using the Open Data Kit app. We measured data completeness, timeliness, and the degree of matching of the data in paper and EHR records, and calculated concordance scores. Factors potentially affecting data quality were drawn from a previous survey of users in the 50 HFs. We randomly selected 3467 patient records, reviewing both paper and EHR copies (194,152 total data items). Data completeness was >85% threshold for all data elements except viral load (VL) results, second-line, and third-line drug regimens. Matching scores for data values were close to or >85% threshold, except for dates, particularly for drug pickups and VL. The mean data concordance was 10.2 (SD 1.28) for 15 (68%) variables. HF and user factors (eg, years of EHR use, technology experience, EHR availability and uptime, and intervention status) were tested for correlation with data quality measures. EHR system availability and uptime was positively correlated with concordance, whereas users' experience with technology was negatively correlated with concordance. The alerts for missing VL results implemented at 11 intervention HFs showed clear evidence of improving timeliness and completeness of initially low matching of VL results in the EHRs and paper records (11.9%-26.7%; P<.001). Similar effects were seen on the completeness of the recording of medication pickups (18.7%-32.6%; P<.001). The EHR records in the 50 HFs generally had high levels of completeness except for VL results. Matching results were close to or >85% threshold for nondate variables. Higher EHR stability and uptime, and alerts for entering VL both strongly improved data quality. Most data were considered fit for purpose, but more regular data quality assessments, training, and technical improvements in EHR forms, data reports, and alerts are recommended. The application of quality improvement techniques described in this study should benefit a wide range of HFs and data uses for clinical care, public health, and disease surveillance.

Application of Lean Six Sigma in Dermatology Practice

The Lean Six Sigma (LSS) methodology integrates two quality improvement techniques to enhance efficiency, reduce waste, and improve the quality of processes and products within an organization. While it has found application in various healthcare settings, to the best of our knowledge, there is currently no literature addressing its utilization in a community dermatology clinic. This study aimed to identify efficiency issues within a local dermatology clinic and implement targeted strategies to bolster collaboration, streamline processes, reduce wait times, augment patient volume, and enhance clinical outcomes and the quality of care. Five areas for improvement were identified: the building complex, front office, EMA system, medical assistants, and general improvements. The executed changes effectively standardized multiple processes, mitigated the potential for errors, and minimized task duration. These findings underscore the efficacy of LSS as a potent tool for enhancing efficiency and reducing waste. Efforts should be directed toward the incorporation of LSS techniques for quality improvement within healthcare systems, both internally and across interconnected entities.

A critical analysis of different power quality improvement techniques in microgrid

A critical analysis of different power quality improvement techniques in microgrid

WaveFormer: transformer-based denoising method for gravitational-wave data

With the advent of gravitational-wave astronomy and the discovery of more compact binary coalescences, data quality improvement techniques are desired to handle the complex and overwhelming noise in gravitational wave (GW) observational data. Though recent machine learning-based studies have shown promising results for data denoising, they are unable to precisely recover both the GW signal amplitude and phase. To address such an issue, we develop a deep neural network centered workflow, WaveFormer, for significant noise suppression and signal recovery on observational data from the Laser Interferometer Gravitational-Wave Observatory (LIGO). The WaveFormer has a science-driven architecture design with hierarchical feature extraction across a broad frequency spectrum. As a result, the overall noise and glitch are decreased by more than one order of magnitude and the signal recovery error is roughly 1% and 7% for the phase and amplitude, respectively. Moreover, on 75 reported binary black hole events of LIGO we obtain a significant improvement of inverse false alarm rate. Our work highlights the potential of large neural networks in GW data analysis and, while primarily demonstrated on LIGO data, its adaptable design indicates promise for broader application within the International Gravitational-Wave Observatories Network in future observational runs.

Improving Compliance with Preoperative Nasal Povidone-Iodine to Prevent Surgical Site Infection in Vascular and Neurosurgery Services in a Community Teaching Hospital.

Surgical site infections (SSI) remain a cause of morbidity, prolonged hospitalization, surgical readmission, and death. Nasal colonization with methicillin-resistant Staphylococcal aureus is a frequent cause of device-related SSI and nasal mupirocin has been used for prevention. More recently, povidone-iodine nasal swabs have become an alternative. It is cheaper, ensures compliance and there are no concerns regarding antimicrobial resistance. However, its adoption was suboptimal in a community hospital system in southwestern Ohio, especially in neurosurgery and vascular surgery. Quality improvement techniques, including solicitation of stakeholder input, surgeons and perioperative nurses' education, and the use of reminders to order and administer the povidone-iodine nasal swabs improved physician ordering and nurse administration compliance, leading to fewer infections. The interventions continued after the project was completed, sustaining decreases in neurosurgery and vascular surgery, and fewer SSI through the first years of the pandemic. Despite the complexity of these surgeries, simple interventions were effective in addressing the problem.

Data mining techniques for quality improvement of electron beam welding process

Besides the fulfilment of the technological requirements for the geometry of the obtained welded joints by electron beam welding, there is a necessity to avoid the conditions, which more probably will lead to defect appearance. It is assumed that the appearance of defects is more probable under some regime conditions. For the modelling of the dependence of bivariate quality characteristics (such as the defect appearance) on the process parameters two different modelling approaches are applied and compared – logistic regression and neural networks. The implemented model-based approaches are compared and applied for the prediction of the defect appearance, depending on the variation of the electron beam process parameters.

Benefits of Preservation, Green and Quality Improvement Investment for Waste Management in Sustainable Supply Chain under Fuzzy Learning and Inflation

In the modern world, waste management, incorporating the quality of the products, energy consumption, and environmental concern have become significant challenges for supply chain managers. Also, smart devices are essential for daily life in the current socioeconomic environment, and customers primarily contemplate a smart product’s price and energy usage before purchasing that. In this situation, to maintain a balance between the selling price, energy consumption, and carbon emission from supply chain operations becomes necessary. So this study develops a twoechelon sustainable inventory model for deteriorating items with an imperfect production process under energy consumption and selling price dependent demand. The producer makes a rework process and quality improvement investment to mitigate defective products and enhance the quality of the products. The present model develops under the influence of inflation. Also, preservation and green technologies are used to mitigate the rate of deterioration and carbon emission, respectively. Firstly, the model is created in a crisp sense, and then expanded into a fuzzy learning model to examine the impact of the learning effect in an imprecise environment. A numerical analysis is performed to validate the proposed model, and the cost function’s convexity is shown graphically using mathematica software. The result of the proposed model provides significant insights to decision-makers on how to efficiently reduce waste while still minimizing the total cost of the system by investing in high efficiency preservation, quality improvement and green techniques. Also, due to learning in fuzziness, the fuzzy learning model gives the lowest total cost, followed by the fuzzy and crisp model. Finally, for various parameters, a sensitivity analysis is performed to gather valuable observations and management insights.

A Comprehensive Survey on Harmonic Elimination in Multilevel Inverters Using Optimization Techniques for Power Quality Improvement

Background: Renewable energy sources offer sustainable solutions, but the conversion of DC energy into AC energy, commonly used in electrical devices necessitates inverters. Multilevel inverters have gained favor over conventional two-level inverters in high-power, mediumvoltage industrial and renewable energy applications due to their high switching frequency capabilities and ability to produce low-harmonic distortion voltage, ensuring superior power quality. Aims: This study focuses on addressing the adverse effects of harmonics in electrical systems and investigates methods to eliminate them in multilevel inverters. Methods: This study summarized current research works on traditional and advanced harmonic removal optimization strategies in multilevel inverters to highlight the limitations, objectives, THD%, and summary of existing works. Moreover, this study applies selective harmonic elimination techniques in 7-level and 15-level inverters using PSO and IPSO optimization algorithms to minimize THD and enhance inverter performance. Results: The study summarizes current research on harmonic removal strategies in multilevel inverters, revealing the prevalent use of MATLAB/Simulink in research endeavors. Various modulation and optimization techniques have been explored to achieve low THD in the output waveform, aligning with IEEE 519 standards for power system harmonic distortion. Furthermore, the comparative analysis part highlights increasing THD improvement with higher inverter levels. The 15-level inverter stands out, achieving 6.75% THD with PSO and 4.12% with improved PSO, meeting IEEE 519's THD limit. Conclusion: The study underscores the importance of ongoing research in this field to advance harmonic reduction strategies, making multilevel inverters even more attractive for a wide range of applications.

Application of Advanced Soft Computing Techniques for Power Quality Improvement Using Active Power Filters in Radial Distribution System

This paper investigates the application of advanced soft computing techniques: northern goshawk optimization (NGO) and coati optimization algorithm (COA) for improving power quality (PQ) using active power filter (APF) in radial distribution systems (RDS). While beneficial, the growing adoption of solar photovoltaic (SPV) systems introduces power quality concerns like harmonic distortion due to their nonlinear nature. This distribution generator (DG) type is called nonlinear DG (NLDG). Harmonics is the leading cause of poor PQ. This study considers nonlinear loads (NLs) at two end nodes and nonlinear DG (NLDG) integrated into the RDS. APFs are optimally placed to reduce the harmonics and enhance PQ. The proposed approach utilizes soft computing techniques to minimize the APF current while adhering to inequality constraints. The NGO, inspired by natural processes, is employed for optimal APF sizing. This method prioritizes a balance between exploration and exploitation for efficient searching. The effectiveness of NGO is evaluated through simulations on the IEEE-69 bus RDS and compared with another recent soft computing technique, the COA. Here, four different cases are considered: a) only NL+NLDG, b) APF at bus 27, c) APF at bus 35, and d) APFs are at 27 and 35 buses. These cases are considered to analyze the effect of placement and sizing of APFs on PQ in RDS. The results validate the stability and efficacy of NGO in addressing this optimization problem for PQ improvement in RDS.

Trustworthiness of Artificial Intelligence Applications for Quality Optimisation in Metal Additive Manufacturing

Market demand is driving the trend towards more individualised products, a phenomenon known as mass customisation. This has spurred the development of innovative technologies, collectively referred to as Industry 4.0. Within this framework, Metal Additive Manufacturing and Artificial Intelligence serve as cornerstone technologies. In manufacturing, Metal Additive Manufacturing promises the ability to efficiently produce low-volume products with reduced lead times. At the same time, it promises greater sustainability, reduced production complexity and improved supply chain resilience. However, the complex physical processes involved are beyond the capabilities of traditional quality improvement techniques such as Statistical Quality Control, necessitating the incorporation of Artificial Intelligence. Although the AI Act seeks to establish a robust regulatory framework to improve the trustworthiness of AI applications, empirical studies substantiating this trust in the context of quality optimisation remain scarce. To address this gap, this study explores the implementation of trustworthy AI in quality optimisation for Metal Additive Manufacturing, evaluating established frameworks and employing state-of-the-art methods to validate the trustworthiness of AI-based quality optimisation techniques. In addition, the physical plausibility and reliability of the AI models are qualitatively checked by process experts.

A comparative study of fuzzy logic based UPQC and D-STATCOM for mitigation of power quality problem

This paper begins by investigating a power quality problem in the case study area using monthly energy consumption data, the peak and minimum load of the substation, a fault summary, and the RMS voltage profile of the case study area. The content of the paper comprises three parts: the first involves MATLAB design and simulation of D-STATCOM with a fuzzy logic controller for the selected case study area. The second part entails MATLAB design and simulation of the DVR with a fuzzy logic controller. The final part presents a hybrid of the DVR and the D-STATCOM back-to-back using a DC link capacitor to implement a more recent and effective power quality improvement technique, namely UPQC. In the case of a three-phase fault, the voltage sag in the case study area is 0.6PU, with the remaining 0.4PU drop-down voltage requiring injection using the proposed FACT device for compensation. All proposed power quality problem mitigation techniques inject the required voltage and compensate for the voltage sag in the substation. For instance, D-STATCOM compensates the RMS voltage from 9KV to 14KV, DVR compensates the RMS voltage from 9KV to 14.7 KV, and UPQC compensates the value to 14.9KV. Due to the three-phase fault, the rise in reactive power of the existing outgoing feeder is 13MW. This unexpected rise in reactive power is reduced to 2.6 MW using D-STATCOM, DVR reduces it to 1.2 MW, and UPQC reduces the value below 1MW. The existing power factor of the case study area without any mitigation technique is 0.68. All proposed techniques improve the existing power factor to a more acceptable value. For instance, D-STATCOM improves the power factor from 0.68 to 0.83, DVR improves the value to 0.88, and UPQC, the more accurate power quality mitigation technique, improves the power factor to 0.93. Finally, the results are compared based on the simulation results.

Seamless Discharge Planning and Care Transition in a Tertiary Hospital

Background: As Singapore's health care landscape evolves to cope with the rapidly ageing society, growing burden of chronic disease and rising health care cost, there is an impetus need to review the hospital's discharge planning process, so as to facilitate timely discharge and safe care transition from hospital to community. In SGH, the role of the Patient Navigator (PN) is to facilitate care coordination, discharge planning and care transition from hospital to community. However, in order to meet the increasing demand and workload, there is a need to look into capability building and empowering all nurses on the essential skills to perform a comprehensive discharge planning. Nurses play a pivotal role in patient/ caregiver's care needs assessment. Having the insight and knowledge will help them facilitate safe, smooth and timely discharge. Patient's discharge planning process is a critical point in care continuity, but it is often complex and challenging. A successful discharge planning involves the proactive identification of care needs and development of individualized care plans.&#x0D; Methods: A pre-survey was done to understand the nurses' knowledge on discharge planning and care transition. 463 nurses responded to this survey. 56% of the nurses rated their knowledge on discharge planning as fair (4 to 7) from a Likert scale of 0 (no knowledge) to 10 (very knowledgeable) (9% rated as poor and 34% rated as good).&#x0D; Hence, this study aims to increase the nurses' knowledge on discharge planning and care coordination, from baseline 34% (good) to 54% (20% improvement) within 6 months.&#x0D; The team used various Quality Improvement tools and techniques, such as the 5-Why diagram to identify the root cause/s to the problem. The final root cause identified was “nurses lack the information and skills” to initiate a comprehensive discharge planning.&#x0D; Intervention: The team then conducted a survey to gather the nurses (stakeholder) feedback on what areas/topics they would like to learn. From the survey results, the team then brainstormed on the delivery mode. Due to the Covid-19 restrictions, the team opted for online e-learning via Wizlearn. The e-learning invitation was then emailed to all Registered Nurses (RNs) in SGH to complete and their feedback was gathered for continued improvement. &#x0D; Results: Post e-learning, the nurses would rate their knowledge gained using a Likert Scale of 0 to 10 (with 0 being no knowledge gained). As of 16 Dec 2021, 504 nurses completed the wizlearn and post-survey. From the pre-post results, there was an increase in ‘Good’ by 27%.&#x0D; P value was statistically significant for “Fair” and “Good” outcomes, p=0.011117. Intangible results include the good feedback received from the nurses in wizlearn stating their appreciation for the information (staff satisfaction). &#x0D; Sustainability plans: The e-learning module is incorporated into the Singhealth e-learning portal and is made available to all staff. New nurses are encouraged to register for this course. The next phase of the project’s sustainability plans includes measuring how the knowledge translates to actual clinical outcome, such as patient’s discharge care plan are documented timely as part of the nurse's assessment.

#253 : Administration of Umbilical Cord-Derived Mesenchymal Stem Cells Secretome to Sperm Preparation Medium: A Pilot Study

Background and Aims: As previously known, umbilical cord-derived mesenchymal stem cells (UC-MSCs) secretome has antioxidant potential that can reduce oxidative and nitrosative stress. This study is very important because understanding the effect of the UC-MSCs secretome on spermatozoa can assist in the development of sperm quality improvement techniques. This study aims to examine the sperm concentration and velocity before and after the addition of UC-MSCs secretome as a modification in sperm preparation with time duration and concentration variation. Method: A pilot study used a secretome produced at Dr. Cipto Mangunkusumo Hospital. Ejaculate samples were collected from married couples who already had children and the results of the semen analysis showed normozoospermia and DNA fragmentation index examination at a good level (15%). Sperm preparation was done using the Swim-up method. Samples were divided into 7 treatments with different ratios of secretions and ejaculate and washing medium (1:1 and 1:2) with incubation time durations (30, 45, and 60 minutes) to find optimal conditions to be used in further studies. The sperm concentration and velocity were observed before and after incubation. Results: Based on the results, it can be observed differences in sperm concentration and velocity from various incubation methods using UC-MSCs secretome. The 1:1 (v/v) secretome treatment had the highest spermatozoa concentration (68 million/mL), while the 1:2 (v/v) secretome treatment had the fastest spermatozoa velocity (30.51 μm/s), with the same incubation time of 45 minutes. The treatment group that was given UC-MSCs secretome 1:1 (60 minutes) and 1:2 (60 minutes) had slower spermatozoa velocity (22.91 μm/s and 21.45 μm/s, respectively) compared to the control group (26.39 μm/s). Conclusion: The administration of UC-MSCs secretome to the sperm preparation medium could increase the concentration and velocity of spermatozoa after incubation. However, this conclusion is provisional and needs further study to support this technique’s development.