A Knowledge Graph-based Learning Assistance Systems for Industrial Maintenance

In recent years, manufacturing execution system (MES) has been widely used in the manufacturing industry. MES plays an important role in supporting enterprise workshop management. However, generalized MES cannot be applied well in steel structure enterprises due to the particularity and complexity of steel structure enterprises. This paper takes into account the production characteristics and needs of steel structure enterprises and an MES structure based on cyber-physical system (CPS) is proposed. This architecture includes the physical layer, the network layer and the application layer. The cloud platform-based MES system was applied to a steel structure enterprise in Changchun, China, and the functions of each module were introduced in detail. The MES can effectively improve the informatization level of the enterprise, creating a transparent, informative and intelligent production environment for steel structure enterprises. The developed MES can improve resource utilization, reduce enterprise costs, improve product quality, and lay the foundation for steel structure enterprises to found intelligent factories.

Abstract—Predictive maintenance (PdM) has emerged as a transformative approach in semiconductor manufacturing, leveraging IoT sensor data to enhance equipment reliability and optimize production processes. This review explores the implementation of predictive maintenance strategies in semiconductor manufacturing, focusing on the role of IoT sensor networks, advanced analytics techniques, and integration with Manufacturing Execution Systems (MES). IoT sensor networks enable comprehensive real-time data collection on equipment performance and environmental conditions, thereby providing a foundation for predictive maintenance. Time series forecasting algorithms, such as ARIMA, exponential smoothing, and machine learning-based approaches, are employed to anticipate potential equipment failures. Anomaly detection techniques, including statistical methods and machine-learning algorithms, are used to identify unusual patterns or behaviors that are indicative of impending issues. The integration of predictive maintenance insights with MES allows for real-time decision making, process optimization, and improved overall equipment effectiveness. However, challenges persist in terms of data quality, scalability, and cybersecurity, requiring ongoing research and industry collaboration. Early adopters reported significant reductions in unplanned downtime, optimized maintenance schedules, and improved product quality. As the semiconductor industry continues to evolve, predictive maintenance is expected to play a crucial role in maintaining competitiveness and meeting the growing demand. Further research, standardization efforts, and development of best practices are essential to fully realize the potential of predictive maintenance in semiconductor manufacturing. Keywords—predictive maintenance (PdM), semiconductor manufacturing, IoT sensor data, equipment reliability, forecasting, anomaly detection, unplanned downtime, product quality

Currently, manufacturing execution systems (MESs) are widely used in the aerospace, automotive, semiconductor, optoelectronic, pharmaceutical and petrochemical industries, as well as other sectors. An MES can link with automation equipment to record relevant information automatically and control the quality of work in process (WIP), statistics analysis, production scheduling and the maintenance of equipment and instruments, etc. In recent years, the manufacturing industry has successfully applied the Six Sigma methodology to projects. However, due to insufficient data or a misunderstanding of the Six Sigma methodology, some of the projects failed. This paper aims to discuss the define, measure, analyse, improve, control (DMAIC) phases of integrating an MES with Six Sigma methodology, detailing the phases to improve the above situation and to avoid the extra time and cost of sourcing data. It will improve the process performance and capability, cycle time, rolled throughput yield and operating costs significantly, which, in turn, improves the quality of implementing the Six Sigma methodology quickly and precisely.

Research background: Risk-taking is the basis for sustainable development of enterprise. It was clear that the influence COVID-19 epidemic on the global market economy has increased operational risks for businesses. The semiconductor industry has high operating risks and financial risks. Moderate financial flexibility (FF) can improve the ability of semiconductor enterprises to acquire financial resources in real time, calmly cope with the impact of uncertainties in operation, improve investment opportunities, and enhance sustainable operation. It is therefore interesting to study the influence of FF on enterprise risk-taking (ERT).
 Purpose of the article: The aim of the contribution is to explore the effect of FF on ERT within Taiwan?s semiconductor industry amid the COVID-19 pandemic period, and investigate whether ERT varies with semiconductor industry characteristic.
 Methods: Data from first three quarters of 2020, from multinational semiconductor firms listed on the Taiwan Stock Exchange (TSE), were collected and analyzed. Fixed effects regression with heteroscedasticity adjustment used to evaluate the influence of FF on the ERT of Taiwan?s semiconductor industry. Furthermore, in order to corroborate and support the reliability of the results, this research also used the different measures of ERT and Quantile regression (median regression) in the research model to check the robustness.
 Findings & value added: Empirical results indicate that FF has a U-shaped effect on ERT for multinational semiconductor firms listed on the TSE, particularly within the integrated circuits (IC) manufacturing industry. Additionally, FF also has a U-shaped effect on ERT for the asset-light semiconductor and IC manufacturing industries. This article also suggests that for the asset-light semiconductor and IC manufacturing industries, the optimal inflection points are 1.1397 and 0.9729, respectively. Based on the consequences of this study, it is suggested that Taiwan?s semiconductor industry should reasonably maintain FF and focus on the liquidity risk management for the long term value added, even after the COVID-19 pandemic period.

Artificial intelligence (AI) is poised to significantly transform the manufacturing industry, with its integration into various processes such as manufacturing, decision-making, and logistics. This paper explores critical areas where AI is being and can be applied: Manufacturing Execution Systems (MES), Supply Chain Management (SCM), Challenges of AI Implementation in Manufacturing and Future Potential of AI in Manufacturing. In the context of MES, AI can optimize production processes, improve real-time monitoring, and enhance decision-making capabilities. Similarly, AI’s impact on SCM is evident through improved forecasting, inventory management, and supply chain visibility. This paper aims to examine the potential applications and explore the opportunities AI offers in these domains, highlighting the ways in which it can revolutionize traditional manufacturing practices. Through a detailed analysis, we identify how AI-driven innovations could reshape manufacturing operations, enhance efficiency, and contribute to the future of the industry. However, challenges such as high implementation costs, information security concerns, and resistance from workers need to be addressed to fully realize AI’s potential. By overcoming these obstacles, AI can redefine the future of manufacturing, making it smarter, more efficient, and sustainable. Reducing manufacturing costs through AI-driven innovations will be crucial for the industry in the near future.

We present a FAB Simulator (FS) and Capacity Planner (CP) that permits the operational planner to introduce new product into an existing production mix with confidence as to the customer delivery dates and FAB Capacity This paper describes the implementation of these two dynamic tools in a semiconductor FAB in Arizona. These tools assist the operational planner with the planning of the daily production mix. This FAB produces 100's of different bipolar devices using 36 process flows. The key to success in calculating present and future production goals is real time operational level tracking. Real time tracked data includes data gathered from the Manufacturing Execution System (MES) for each product's work-in-process (WIP), process flow routing, and data gathered from the equipment utilization and emergency maintenance databases. This key information is fed through a GUI linked to the CP which in turn controls the stochastic dynamic simulation model of the FS. These links provide the operational planner with dynamic production data in real time and simulated time for decision-making. The CP and FS are running in parallel and are linked directly with the FAB's MES maintaining current production data.

Aims: This study examines the relationship between nutritional quality, work stress, and anxiety of individuals working in different positions in industrial organizations. Material and Methods: A total of 132 volunteers, aged 18-65, employed in industries in İstanbul, underwent assessments. The study employed the Work Stress Scale and Beck Anxiety Inventory for work stress and anxiety measurements and the Healthy Eating Index-2015 (HEI-2015) for diet quality, using 24-hour food records. Results: In this research, 48.9% of white-collar employees and 49.4% of blue-collar employees experience high levels of job stress (p>0.05). Anxiety was found in 48.9% of white-collar workers and 39.1% of blue-collar workers (p>0.05). The diet quality of 75.6% of white-collar workers and 72.4% of blue-collar workers was poor. Statistically significant differences were identified when comparing job stress with the Beck Anxiety Inventory and HEI-2015 results (p=0.005 and p=0.030, respectively). Blue-collar industrial workers reported higher daily energy intake (2277.3 kcal) and carbohydrates (295.5±77.50 g/day) compared to white-collar workers (energy 1979.1 kcal; carbohydrates 261.2±78.61 g/day), with significant differences in calorie and carbohydrate consumption (p=0.015). Noteworthy dietary habits influencing work stress included skipping snacks (p

Study objective: Occupational structure represents the unequal geographical distribution of more desirable jobs among communities (for example, white collar jobs). This study examines joint effects of social class, race, and...

BackgroundThe area of Gela was included among the 57 Italian polluted sites of national interest for environmental remediation because of its widespread contamination from a petrochemical complex. The present study investigates mortality and morbidity of the cohort of Gela petrochemical workers with the aim of disentangling occupational from residential risk.MethodsMortality was assessed for 5,627 men hired from 1960, year of the plant start-up, to 1993; it was followed up for vital status in the period 1960–2002. Morbidity was analysed for 5,431 workers neither dead nor lost to follow-up from 1960 to 2001 and was based on Hospital Discharge Records in the period 2001–2006. The work experience was classified in terms of job categories such as blue collars, white collars, and both – workers who shifted from blue to white collar (95%) or vice versa. An ad hoc mobility model was applied to define qualitative categories of residence in Gela, as residents and commuters. Standardized Mortality Ratios (SMRs) and Mortality Rate Ratios (MRRs) were computed, the latter by using a Poisson regression model. Morbidity was analyzed in terms of Hospital Discharge Odds Ratios (HDORs) through a logistic regression model. While performing the internal comparisons, white collars was the reference category for the job analysis, and commuters was the reference category for the residential analysis.ResultsIn the light of epidemiological evidence about health risk from petrochemical industries in both occupational and environmental settings, and/or on the basis of information about occupational and residential contamination and health risk in the area of Gela, noteworthy results are shown for lung cancer [MRR: 2.11 (CI 90%; 0.96-4.63) in blue collars; 1.71 (1.09-2.69) in residents], respiratory diseases [HDOR: 2.0 (1.0-3.0) in blue collars; 1.4 (0.96-2.06) in residents] and genitourinary diseases [HDOR: 1.34 (1.06-1.68) in blue collars; 1.23 (1.04-1.45) in residents].ConclusionsThe results support a role of the exposures in the occupational and residential settings, the latter due to the local ascertained contamination, in affecting the workers’ health. These results underline the urgent need of water, soil, air and food-chain monitoring programs, to discover active sources of exposure and consequently define public health interventions.

Background It is well known that occupational activity can affect health. The association between type of work and Inflammatory Bowel Diseases (IBD) has been studied previously, but the studies on the topic are scarce and they do not have studied the relationship with clinical activity of the disease. The aim of this study is to elucidate if the type of work is a risk factor for the disease activity and severity in recently diagnosed IBD patients. Methods An observational prospective study including incident cases of patients with IBD diagnosed between June 2020 and September 2022 in the area of Santiago de Compostela was developed. Type of work, divided into white collar and blue-collar, sedentariness at work divided into high activity, moderate activity and sedentary activity according to the classification of occupational activity categories using accelerometry, and place of work divided into indoor and outdoor, time at work and contact with animals at work was recorded. All cases were followed-up through one year to assess the evolution of the disease. Endoscopic index at one year from the diagnosis, analytic parameters, hospitalizations related with the disease during the period, treatments administered, and number and severity of flares (measured by Partial Mayo Score and Harvey- Bradshaw) were collected. To analyze the results, a logistic regression was used. Results 136 patients were included and followed their activity for a year. 68 (50%) were females. 78 (57.4%) had ulcerative colitis, 52 (38.2%) Crohn’s disease and 6 (4.4%) unclassified colitis. 30 patients (22.1%) had at least one flare during this time (23 had 1 flare, 5 two and 2 three), and 4 patients were primary non responders. 7 patients (5.2%) were hospitalized. Neither the type of job (white or blue collar), time at work (working hours per week), physical activity at work (sedentary work, moderate activity or high activity), working outdoor vs. indoor nor contact with animals at work were associated with hospitalization (all p>0.05). When contact with chemicals, solvents and dusts were analyzed, no statistically significant difference was found (p>0.05). Regarding the appearance of flares, high activity at work and working outside were protective factors of the appearance of a flare, with OR 0.1 (0.0 – 0.7) and 0.2 (0.1 – 0.8) respectively (Table 1).After stratifying results according to type of IBD, there were no statistically significant differences. Conclusion High activity jobs and working outside are protective factors for a flare appearance in patients with recent diagnosis of IBD. Type of job it is not related with risk of hospitalization.

To investigate the association between sarcopenia, sarcopenic obesity (SO), metabolic syndrome (MetS), and occupational history. Using data from the Korea National Health and Nutrition Examination Survey, men more than or equal to 65 years of age (n = 679) were grouped according to occupation. Mean skeletal muscle mass index was higher and mean body fat mass was lower in agribusiness and low-level (AL) workers than white-collar (WC), blue-collar (BC), and pink-collar (PC) workers. The risk of sarcopenia was highest in BC, followed by WC, PC, and AL. The risk of SO was higher in WC than AL and MetS was higher in WC and BC than AL. The development of sarcopenia, SO, and MetS is related to lifetime occupation, with BC workers being most affected by sarcopenia and WC workers being most affected by SO and MetS.

To realize smart manufacturing in Industry 4.0, we have to employ a lot of sensors to capture manufacturing information to identify the current status of production lines. On other hand, the job coordinator should assign tasks according to not only equipment status in production lines but also management systems, such as enterprise resource planning system and manufacturing execution system. A possible solution of the job coordinator is the cyber-physical system (CPS). CPS evaluate the production capability by equipment status and management systems via the manufacturing data. In most considerations of CPS, adjusting the setting of production lines to fit the requirements from management systems, e.g. the received orders. However, it is hard to reach smart manufacturing in the above consideration. From our empirical observation, not only the setting of production lines should be adjusted, but also the management systems should also be adjusted for finding a balance purpose. Therefore, we present a novel idea to generate the decision for reaching optimal producing for CPS.

Industry 4.0 has placed an emphasis on real-time decision making in the execution of systems, such as semiconductor manufacturing. This article will evaluate a scheduling methodology called Evolutionary Learning Based Simulation Optimization (ELBSO) using data generated by a Manufacturing Execution System (MES) for scheduling a Stochastic Job Shop Scheduling Problem (SJSSP). ELBSO is embedded within Ordinal Optimization (OO), where in the first phase it uses a meta model, which previously was trained by a Discrete Event Simulation model of a SJSSP. The meta model used within ELBSO uses Genetic Programming (GP)-based Machine Learning (ML). Therefore, instead of using the DES model to train and test the meta model, this article uses historical data from a front-end fab to train and test. The results were statistically evaluated for the quality of the fit generated by the meta-model.

This paper examines whether retirement differentially affects body mass index (BMI) patterns by occupation; occupation embodies differences in on-the-job physical demands as well as socioeconomic characteristics that could lead to variation in post-retirement BMI. We use 12 years of national data from the US and hierarchical linear models to compare BMI trajectories among four broad occupational classes. We find that those in service and other blue-collar occupations have significant increases in the slopes of their BMI trajectories after retirement, whereas participants in white-collar occupations exhibit no change. This may be due to differences in the physical requirements across blue and white collar jobs or differences in health habits post-retirement. Retirement may provide an opportunity to help prevent obesity in older individuals, especially blue collar workers.

Minimal hepatic encephalopathy (HE) is a major cause of premature retirement in cirrhotics. The decision on the earning capability of a patient is usually based on clinical judgement, considering the patient's complaints and clinical findings such as nervousness and depression. In a comprehensive psychometric study we were able to show that cirrhotic patients, who are considered to be unable to earn their living, differ significantly from those who are working, in tests evaluating psychomotor function and in personality and subjective well-being scores representing nervousness, aggressiveness, depression. The latter scores are considered to represent the individual discrepancies between professional demands and cerebral performance. Since minimal HE affects psychomotor function but not verbal abilities this discrepancy exists predominantly in "blue collar workers." In accordance with this 60% of "blue collar" (in contrast to 20% of "white collar") workers of our patient group were considered unfit for work. Working ability is an essential element of quality of life in Western societies. Thus, an impairment of working capability is of major impact on quality of life in cirrhotics.