Real-time Production Research Articles

Analisis Manajemen Produksi Pertanian Hidroponik Berbasis IoT (Internet of Things) di Wisata Edukasi Arjuna Farm Kecamatan Tamansari Kota Tasikmalaya

The tourism sector in Indonesia is growing rapidly thanks to the abundant natural, social, cultural and regional potential. One educational tourist attraction that is currently developing is Arjuna Farm in Tasikmalaya City, which offers the concept of integrating the agricultural and fisheries sectors with the application of IoT (Internet of Things) technology. This research aims to analyze the application of IoT technology to support hydroponic production management at Arjuna Farm, especially in increasing the effectiveness, efficiency and quality of agricultural products. The research used a case study approach with a qualitative descriptive method, involving direct observation, in-depth interviews with the main managers (Mr. Andi and Mrs. Selvi), as well as analysis of secondary data from various literary sources. The research location was chosen by purposive sampling, located at Jalan Situ Cibereum, Tamanjaya, Tamansari, Tasikmalaya City, during November 2024. The research results show that POAC (Planning, Organizing, Actuating and Controlling) based management is implemented well, supported by IoT systems such as automatic watering, drip irrigation. This technology enables efficient and real-time production management, thereby maintaining the quality and sustainability of harvests, as well as increasing the attractiveness of Arjuna Farm as an educational tourist attraction based on modern technology.

Fired Heaters Optimization by Estimating Real-Time Combustion Products Using Numerical Methods

Fired heaters upstream of distillation towers, despite their optimal thermal efficiency, often suffer from performance decline due to fluctuations in fuel composition and unpredictable operational parameters. These heaters have high energy consumption, as fuel properties vary depending on the source of the crude oil. This study aims to optimize the combustion process of a three-gas mixture, mainly refinery gas, by incorporating more stable fuels such as natural gas and liquefied petroleum gas (LPG) to improve energy efficiency and reduce LPG consumption. Using real-time gas chromatography-mass spectrometry (GC-MS) data, we accurately calculate the mass fractions of individual compounds, allowing for more precise burner flow rate determinations. Thermochemical data are used to calculate equilibrium constants as a function of temperature, with the least squares method, while the Newton–Raphson method solves the resulting nonlinear equations. Four key variables (X4,X6,X8, and X11), representing H2,CO,O2, and N2, respectively, are defined, and a Jacobian matrix is constructed to ensure convergence within a tolerance of 1 ×10−6 over a maximum of 200 iterations, implemented via Python 3.10.4 and the scipy.optimize library. The optimization resulted in a reduction in LPG consumption by over 50%. By tailoring the fuel supply to the specific thermal needs of each processing unit, we achieved substantial energy savings. For instance, furnaces in the hydrocracking unit, which handle cleaner subproducts and benefit from hydrogen’s adiabatic reactions, require much less energy than those in the primary distillation unit, where high-impurity crude oil is processed.

"Are my blood products coming?": Implementation of a novel blood product tracker in the electronic health record system.

Blood transfusions are the most common procedure performed in American hospitals. The steps required for blood product delivery are often misunderstood by providers, leading to numerous phone calls to the blood bank requesting order status. Distracting calls can lengthen turnaround time, especially during blood product or staff shortages. We sought a tool to address these questions and reduce distraction. This study highlights a novel blood tracker tool implemented in the electronic health record (EHR) that allows providers to see their blood order's status. With a multidisciplinary team of healthcare professionals, we constructed a user-friendly blood tracker highly visible in our EHR. It shows the status of a blood product in real time from "order printed" to "preparing" to "on its way." We surveyed blood bank technologists to determine if call volume and distraction changed. We counted the number of views per month as a surrogate of usage. The blood tracker was viewed 109,626 times per month on average from January through December 2023. The fraction of technologists who received 21 or more calls per shift decreased by 47%. We successfully constructed and implemented a novel blood tracker into our EHR that relays the status of a blood product. It is a highly viewed piece of information in our EHR and decreases blood bank call volume as reported by blood bank technologists. Its success demonstrates that closed-loop communication between the lab and providers regarding blood products is beneficial within our organization and potentially others.

Combining Galileo HAS and Beidou PPP-B2b with Helmert coordinate transformation method

The European Galileo High Accuracy Service (HAS) started to provide freely and openly accessible real-time precise satellite orbit, clock and code bias products to global users on January 24, 2023. Combined with the already running BeiDou PPP-B2b service, the launch of a variety of satellite-based PPP services provided more choices to users. However, different satellite-based PPP services provide services for different GNSS systems, which hamper users to make full use of multi-GNSS systems. Therefore, the combination of different satellite-based products can further improve the availability of corrections, usage of multi-GNSS observation data and positioning performance. This paper proposes to combine HAS and PPP-B2b products by the Helmert coordinate transformation method. To validate the algorithm, HAS and PPP-B2b products of day of year (DOY) 308–317 in 2023 were collected in Zhengzhou, China. First, they are evaluated in terms of correction availability, orbit and clock quality. Then the HAS and PPP-B2b products are combined by the Helmert coordinate transformation method. Two combination strategies are proposed. The first strategy is integrating BDS satellites of PPP-B2b products into HAS products (denoted as C_H), while the second strategy is integrating Galileo satellites of HAS products into PPP-B2b products (denoted as C_B). Finally, the combined strategies are evaluated with static and kinematic data. Based on the static data of 18 Multi-GNSS Experiment (MGEX) stations in China and its surrounding areas, the results show that, when separately using HAS and PPP-B2b products for PPP, the average accuracy in horizontal and vertical directions are (2.4, 2.7 cm) and (2.4, 2.0 cm), respectively. The average accuracy of C_H strategy is 2.1 and 1.7 cm, which was improved by 31.3% compared with separately using the products. Similarly, the average accuracy of C_B strategy is 2.1 and 1.9 cm, corresponding to improvements of 29.6%. When comparing the two combined strategies, it is noted that the C_B strategy converges faster. Based on the data from vehicle platform, the results show that the horizontal and vertical accuracy of the C_B strategy is 8.6 and 15.7 cm respectively. The accuracy improvement of C_B is better than that of C_H strategy, and the average accuracy is 68.4% better than that of separately using the products. The above results show that the two combined strategies can improve positioning accuracy. In addition, the improvements in accuracy and convergence speed of C_B strategy are more significant. Users are advised to use C_B strategy for the combination of HAS and PPP-B2b products, which will greatly expand the application of HAS and PPP-B2b services.

A Q-learning driven multi-objective evolutionary algorithm for worker fatigue dual-resource-constrained distributed hybrid flow shop

In practical industrial production, workers are often critical resources in manufacturing systems. However, few studies have considered the level of worker fatigue when assigning resources and arranging tasks, which has a negative impact on productivity. To fill this gap, the distributed hybrid flow shop scheduling problem with dual-resource constraints considering worker fatigue (DHFSPW) is introduced in this study. Due to the complexity and diversity of distributed manufacturing and multi-objective, a Q-learning driven multi-objective evolutionary algorithm (QMOEA) is proposed to optimize both the makespan and total energy consumption of the DHFSPW at the same time. In QMOEA, solutions are represented by a four-dimensional vector, and a decoding heuristic that accounts for real-time worker productivity is proposed. Additionally, three problem-specific initialization heuristics are developed to enhance convergence and diversity capabilities. Moreover, encoding-based crossover, mirror crossover and balanced mutation methods are presented to improve the algorithm’s exploitation capabilities. Furthermore, a Q-learning based local search is employed to explore promising nondominated solutions across different dimensions. Finally, the QMOEA is assessed using a set of randomly generated instances, and a detailed comparison with state-of-the-art algorithms is performed to demonstrate its efficiency and robustness.

Impact of Latency and Continuity of GNSS Products on Filter-Based Real-Time LEO Satellite Clock Determination

High-precision Low Earth Orbit (LEO) satellite clocks are essential for LEO-augmented Positioning, Navigation, and Timing (PNT) services. Nowadays, high-precision LEO satellite clocks can be determined in real-time using a Kalman filter either onboard or on the ground, as long as the GNSS observations collected onboard LEO satellites can be transmitted to the ground in real-time. While various real-time and high-precision GNSS products are available nowadays in the latter case, their continuity and latencies in engineering reality are not as perfect as expected and will lead to unignorable impacts on the precision of the real-time LEO satellite clocks. In this study, based on real observations of Sentinel-3B, the impacts of different latencies and continuity of the real-time GNSS products on LEO real-time clocks are determined and discussed for two scenarios, namely the “epoch estimation” and “arc estimation” scenarios. The former case refers to the traditional filter-based processing epoch-by-epoch, and the latter case connects LEO satellite clocks from different rounds of filter-based processing under a certain arc length. The two scenarios lead to the “end-loss” and “mid-gap” situations. Latencies of the real-time GNSS products are discussed for the cases of orbit-only latency, clock-only latency, and combined forms, and different handling methods for the missing GNSS satellite clocks are discussed and compared. Results show that the real-time LEO satellite clock precision is very sensitive to the precision of real-time GNSS satellite clocks, and prediction of the latter becomes essential in case of their latencies. For the “end-loss” situation, with a latency of 30 to 120 s for the GNSS real-time clocks, the LEO satellite clock precision is reduced from about 0.2 to 0.28–0.57 ns. Waiting for the GNSS products in case of their short latencies and predicting the LEO satellite clocks instead could be a better option. For “arc-estimation”, when the gap of GNSS real-time products increases from 5 to 60 min, the real-time LEO clock precision decreases from 0.26 to 0.32 ns.

The metabolic engineering of Escherichia coli for the high-yield production of hypoxanthine

BackgroundHypoxanthine, prevalent in animals and plants, is used in the production of food additives, nucleoside antiviral drugs, and disease diagnosis. Current biological fermentation methods synthesize quantities insufficient to meet industrial demands. Therefore, this study aimed to develop a strain capable of industrial-scale production of hypoxanthine.ResultsDe novo synthesis of hypoxanthine was achieved by blocking the hypoxanthine decomposition pathway, thus alleviating transcriptional repression and multiple feedback inhibition, and introducing a purine operon from Bacillus subtilis to construct a chassis strain. The effects of knocking out the IMP(Inosine 5’-monophosphate) branch on the growth status and titer of the strain were then investigated, and the effectiveness of adenosine deaminase and adenine deaminase was verified. Overexpressing these enzymes created a dual pathway for hypoxanthine synthesis, enhancing the metabolic flow of hypoxanthine synthesis and preventing auxotrophic strain formation. Introducing IMP-specific 5’ -nucleotidase addressed the issue of adenylate accumulation. In addition, the metabolic flow of the guanine branch was dynamically regulated by the guaB gene. The supply of glutamine and aspartic acid precursors was enhanced by introducing an exogenous glnA mutant gene, overexpressing aspC, and replacing the weaker promoter to regulate the aspartic acid branching pathway. Ultimately, fermentation in a 5 L bioreactor for 48 h produced 30.6 g/L hypoxanthine, with a maximum real-time productivity of 1.4 g/L/h, the highest value of hypoxanthine production by microbial fermentation reported so far.ConclusionsThe intracellular purine biosynthesis pathway is extensive and regulated at multiple levels in cells. The IMP branch in the hypoxanthine synthesis pathway has a higher metabolic flux. The current challenge lies in systematically allocating the metabolic flux within the branch pathway to achieve substantial product accumulation. In this study, E. coli was used as the chassis strain to construct a dual pathway for IMP and AMP(Adenosine 5’-monophosphate) synergistic hypoxanthine synthesis and dynamically regulate the guanine branch pathway. Overall, our experimental efforts culminated in a high-yield, plasmid- and defect-free engineered hypoxanthine strain.

Task offloading for multi-server edge computing in industrial Internet with joint load balance and fuzzy security

The industrial Internet revolutionizes traditional manufacturing through the incorporation of technologies such as real-time production optimization, big data analysis, etc. Computing resource-constrained industrial terminals struggle to effectively execute latency-sensitive and computation-intensive tasks triggered by these technologies. Edge computing (EC) emerges as a promising paradigm for offloading tasks from terminals to the adjacent edge servers, offering the potentiality to augment the computational capacities for industrial terminals. However, the development of accurate offloading strategies poses a prominent challenge for EC in the industrial Internet. Incorrect offloading strategies will misguide the task offloading procedure, resulting in adverse consequences. In this paper, we study the latency-aware multi-server partial EC task offloading problem in the industrial Internet with the consideration of joining load balancing and security protection to provide accurate strategies. Firstly, we establish a task offloading model that supports partial offloading, facilitating latency reduction, task offloading across multiple edge servers with load balance, and accommodation of fuzzy task risks. We quantify the established model as a constrained optimization formulation and prove its NP-hardness. Secondly, to solve the composite offloading strategy comprising both the offloading location and offloading ratio derived from our model, we propose a bi-layer offloading algorithm with joint load balance and fuzzy security, which is based on the adaptive genetic algorithm and simulated annealing particle swarm optimization. Based on extensive experimental results, we find that the established model is effective in reducing the objective value, with a respective decrease of 27% and 46% compared to full execution in edge servers and local execution in industrial terminals. Furthermore, the proposed offloading algorithm exhibits superior performance in terms of solution accuracy compared to existing algorithms.

Towards Real-Time Integrated Water Vapor Estimates with Triple-Frequency Galileo Observations and CNES Products

Integrated water vapor (IWV) is a crucial parameter for tropospheric sounding and weather prediction applications. IWV is essentially calculated using observations from global navigation satellite systems (GNSS). Presently, the Galileo satellite system is further developed, including more visible satellites that transmit multi-frequency signals. This study aims to evaluate the accuracy of real-time IWV estimated from a triple-frequency Galileo-only precise point positioning (PPP) processing model utilizing E1, E5a, E5b, and E5 observations, which is not addressed by the previous studies. For this purpose, Galileo datasets from 10 global reference stations spanning various 4-week periods in the winter, spring, summer, and fall seasons are acquired. To process the acquired datasets, dual- and triple-frequency ionosphere-free PPP solutions are used, including E1E5a PPP, E1E5aE5b PPP, and E1E5E5b PPP solutions. The publicly available real-time products from the Centre National d’Etudes Spatiales (CNES) are utilized. The real-time IWV values are computed and then validated with the European Centre for Medium-Range Weather Forecasting (ECMWF) reanalysis products (ERA5) counterparts. The findings demonstrate that the root mean square error (RMSE) of the estimated IWV is less than 3.15 kg/m2 with respect to the ECMWF ERA5 counterparts. Furthermore, the E1E5aE5b PPP and E1E5E5b PPP models enhance the IWV’s accuracy by about 11% and 16%, respectively, compared with the E1E5a PPP model.

The influence of business intelligence on the effectiveness of supply chain management in the Nigerian consumer goods sector

Business performance depends on supply chain management (SCM), which can be enhanced through digital transformation to enable quick decisions to increase market share. By enabling informed decision-making, business intelligence (BI) can facilitate this improvement in SCM effectiveness and competitive edge. Real-time production and inventory level monitoring is made possible by BI capabilities, which help organisations adapt to changing market trends and meet customer demands. Particularly, BI technology can increase the SCM of enterprises in the consumer products sector by providing value-added and financial gains, enabling speedy industry adoption and rapid industry growth. The study employed a quantitative methodology for gathering data, and a simple random sampling method was employed to prevent sample bias. The study considered linear curve estimation (LCE) as a method of data analysis. The results of the model estimations showed that BI recorded positive and significant influence on SC visibility, flexibility, and resilience in the Nigerian consumer goods sector. The study concludes that BI increased the effectiveness of supply chain management (SCM) by improving visibility, anticipating demand, increasing resilience, optimising processes, and boosting productivity. SCM effectiveness depends on the efficient handling of disruptions and uncertainty. The study highlights the practical policy implications following the findings of the study.

Role of Live E-Commerce on Consumer Purchase Intentions

Purpose: One of the many ways that e-commerce allows shops to use live video to promote products in real time is live streaming. Theoretical structure: Perceived value and trust received are important factors of cognitive response showing interaction with external stimuli in the context of online purchasing study. Approach, methodology, and design: In the end, it influences the customers' information-seeking behaviour and helps the business create long-term profits by providing information and enabling synchronous information exchange between the online viewer (consumer) and the Internet celebrity. China has set the standard for innovation in internet commerce worldwide, from live broadcasting to cutting-edge purchasing. Results: For live commerce, social engagement, entertainment, and buy intent were found to be positively correlated. However, no relationship between purchase intent and professionalisation or visualisation was found. During live streaming, entertainment has the most influence on viewers' intention to purchase. Research, Practical, and Social Implications: With the quick advancement of contactless communication, it is projected that the live-streaming e-commerce sector will keep expanding. E-commerce that is live-streamed transcends the traditional notion of solely selling products or services. Originality/value: This study can be used as a standard by future academics and business experts to boost viewers' propensity to make a purchase while live streaming.

Soft-sensor model development for CHO growth/production, intracellular metabolite, and glycan predictions.

Efficaciously assessing product quality remains time- and resource-intensive. Online Process Analytical Technologies (PATs), encompassing real-time monitoring tools and soft-sensor models, are indispensable for understanding process effects and real-time product quality. This research study evaluated three modeling approaches for predicting CHO cell growth and production, metabolites (extracellular, nucleotide sugar donors (NSD) and glycan profiles): Mechanistic based on first principle Michaelis-Menten kinetics (MMK), data-driven orthogonal partial least square (OPLS) and neural network machine learning (NN). Our experimental design involved galactose-fed batch cultures. MMK excelled in predicting growth and production, demonstrating its reliability in these aspects and reducing the data burden by requiring fewer inputs. However, it was less precise in simulating glycan profiles and intracellular metabolite trends. In contrast, NN and OPLS performed better for predicting precise glycan compositions but displayed shortcomings in accurately predicting growth and production. We utilized time in the training set to address NN and OPLS extrapolation challenges. OPLS and NN models demanded more extensive inputs with similar intracellular metabolite trend prediction. However, there was a significant reduction in time required to develop these two models. The guidance presented here can provide valuable insight into rapid development and application of soft-sensor models with PATs for ipurposes. Therefore, we examined three model typesmproving real-time product CHO therapeutic product quality. Coupled with emerging -omics technologies, NN and OPLS will benefit from massive data availability, and we foresee more robust prediction models that can be advantageous to kinetic or partial-kinetic (hybrid) models.

LEO satellite clock modeling and its benefits for real-time LEO PPP timing

In the kinematic Precise Orbit Determination (POD) process for low earth orbit (LEO) satellites, a significant correlation exists between the orbital and clock parameters. Here, a LEO satellite clock model is proposed to enhance the Precise Point positioning (PPP) timing and time synchronization during the LEO orbit/clock determination. The GRACE-FO satellite was utilized to achieve PPP timing and time transfer for LEO satellites with the real-time (RT) products provided by three analysis centers, namely Centre National d’Etudes Spatiales (CNES), GMV Aerospace and Defense (GMV), and Wuhan Technical University (WHU). For the frequency stability of the PPP timing for LEO satellites, the short-term stability (1280 s) is about 10−13 level, and the long-term stability (10,240 s) is about 10−14 level. Compared with the traditional PPP method (Scheme1), the LEO satellite clock model (Scheme2) is capable of significantly reducing the noise, regardless of whether it is PPP timing or PPP time synchronization. The frequency stability of Scheme 1 shows an improvement in short-term stability (1280 s) by about 8 %-72 % and the max improvement of the long-term stability (10240 s) by approximately 39 %, the result also shows a better improvement in LEO time synchronization.

In-depth exploration of waste printed circuit boards pyrolysis: Real-time products characteristics, kinetics parameter optimization and reaction mechanism

Pyrolysis is a promising technology for recycling waste printed circuit boards (WPCBs). This study delves into a real-time examination of the volatiles emitted from WPCBs during pyrolysis using thermogravimetric analysis coupled with Fourier transform infrared spectroscopy/mass spectrometry (TG-FTIR/MS), offering an in-depth analysis of the entire pyrolysis mechanism. An optimized kinetic model for printed circuit board (PCB) pyrolysis is developed by the shuffled complex evolution (SCE) algorithm. Results indicate that the main pyrolysis products are phenol and alkyl-substituted phenols, along with hydrogen bromide (HBr) and bromophenols. Bromides exhibit an earlier onset and peak temperature compared to phenolic products. The pyrolysis process can be divided into two stages: initial depolymerization of the resin body into macromonomers, followed by prevalent alkyl removal, homolytic reactions, and isomerization. The apparent activation energy (E) is 155.32 kJ/mol, the pre-exponential factor (ln(A)) is 29.77 min−1, and the kinetic mechanism function is described by (1‐α)2.02. This study provides crucial knowledge to advance the technology of WPCBs pyrolysis.

Anion Effect in Electrochemical CO2 Reduction: From Spectators to Orchestrators.

The electrochemical CO2 reduction reaction (eCO2RR) offers a pathway to produce valuable chemical fuels from CO2. However, its efficiency in aqueous electrolytes is hindered by the concurrent H2 evolution reaction (HER), which takes place at similar potentials. While the influence of cations on this process has been extensively studied, the influence of anions remains largely unexplored. In this work, we study how eCO2RR selectivity and activity on a gold catalyst are affected by a wide range of inorganic and carboxylate anions. We utilize in situ differential electrochemical mass spectrometry (DEMS) for real-time product monitoring coupled with molecular dynamics (MD) simulations. We show that anions significantly impact eCO2RR kinetics and eCO2RR selectivity. MD simulations reveal a new descriptor─free energy of anion physisorption─where weakly adsorbing anions enable favorable CO2 reduction kinetics, despite the negative charge carried by the electrode surface. By leveraging these fundamental insights, we identify propionate as the most promising anion, achieving nearly 100% Faradaic efficiency while showing high CO production rates that are comparable to those in bicarbonate. These insights underscore the vital role of anion selection in achieving a highly efficient eCO2RR in aqueous electrolytes.

Construction of a Digital Twin System and Dynamic Scheduling Simulation Analysis of a Flexible Assembly Workshops with Island Layout

Assembly Workshops with Island Layout (AWIL) possess flexible production capabilities that realize product diversification. To cope with the complex scheduling challenges in flexible workshops, improve resource utilization, reduce waste, and enhance production efficiency, this paper proposes a production scheduling method for flexible assembly workshops with an island layout based on digital twin technology. A digital twin model of the workshop is established according to production demands to simulate scheduling operations and deal with complex scheduling issues. A workshop monitoring system is developed to quickly identify abnormal events. By employing an event-driven rolling-window rescheduling technique, a dynamic scheduling service system is constructed. The rolling window decomposes scheduling problems into consecutive static scheduling intervals based on abnormal events, and a genetic algorithm is used to optimize each interval in real time. This approach provides accurate, real-time scheduling decisions to manage disturbances in workshop production, which can enhance flexibility in the production process, and allows rapid adjustments to production plans. Therefore, the digital twin system improves the sustainability of the production system, which will provide a theoretical research foundation for the real-time and unmanned production scheduling process, thereby achieving sustainable development of production.

Tropospheric delay estimation and influencing factors analysis of GNSS multi-system

Abstract In this paper, the tropospheric delay parameters are estimated by GNSS regional network solution, and the different factors affecting the estimation of tropospheric delay parameters are analyzed experimentally. The high-precision tropospheric delay correction file (.ztd) provided by IGS and the traditional model estimation of the GNSS regional network are compared to verify the final positioning accuracy. The main factors affecting the estimation of tropospheric delay parameters and the conditions conducive to the estimation of tropospheric delay parameters in the data solution process are obtained. The experimental results show that: (1) GPS has the highest tropospheric delay estimation accuracy in the European region, Galileo is slightly worse than GPS, and BDS has the lowest tropospheric delay estimation accuracy; (2) The tropospheric delay estimation accuracy of post-product in different satellite precision products is better than that of real-time products, and CLKM2 is better than CLK93 in real-time products. With the increase of satellite systems, the accuracy of tropospheric delay estimation is gradually improved. Compared with the GPS single system, the accuracy of the GPS+ Galileo+BDS triple system is improved by about 7.2%, 7.2%, and 7.5%; (3) The tropospheric delay estimation accuracy of the European region is better than that of the Australian region; (4) Based on the BDS whole system data solution, the high-precision tropospheric delay correction file (.ztd ) has better positioning accuracy, and the tropospheric delay estimated by the GNSS observation data through the traditional Saastamoninen model of the regional network can also meet the current high-precision positioning requirements in terms of positioning accuracy. The horizontal direction is better than 2 cm, and the elevation direction is better than 4 cm.

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.

Soft sensor for melting flow rate prediction based on data-enhanced classification method

Abstract The melt flow rate (MFR) is a crucial quality indicator for polyolefin products. However, the offline laboratory measurement method suffers from significant time delays between sampling and obtaining test values, making it inconvenient for real-time product quality control. Additionally, installing an online analyzer can be expensive. In this study, we propose a soft sensor method that combines mechanism analysis and data-driven approaches to predict the MFR in the extruder process. Firstly, we analyze the physical mechanism of the extruder process, and the time series data are processed into independent enhanced data sets by reasonably selecting data enhancement parameters. Secondly, we statistically model the distribution of particle MFR and classify the data into four sections. We train Deep Neural Network (DNN) and Gradient Boosting Decision Tree (GBDT) regression models separately for low and non-low MFR sections while also developing a global classification model to invoke corresponding regression models when needed. The results demonstrate that our classification model achieves 100% accuracy in distinguishing between low and non-low MFR categories; furthermore, our regression models achieve an RMSE of 0.600, and an R2 value of 0.998, outperforming existing models on various indicators. Finally, considering viscosity variations in polyolefin products' influence on prediction performance, we recommend setting data enhancement parameters contrary to particle MFR trends.

ResNet-101 based anomaly detection in additive manufacturing: Thermal modeling for quality control in heat exchanger production

In the production of heat exchangers using additive manufacturing, maintaining consistent quality is a significant challenge due to irregular energy transformations during the manufacturing process. These irregularities can result in faulty products, leading to issues such as reduced efficiency and reliability of the heat exchangers. Traditional quality control methods are often inadequate for real-time detection and correction of such faults. This paper focuses on analyzing the occurrence of faulty products caused by irregular energy transformations in heat exchangers. A deep learning network, specifically ResNet-101, is employed to address this issue. The network is trained with characteristic features of the product and instantaneous variations in the heat exchanger to accurately identify faulty patterns resulting from degradation in the heat exchanger’s performance. By leveraging the deep learning network, which comprehensively understands both the product and heat exchanger features, the system can detect and classify faulty products in real time. This enables immediate corrective actions, such as pushing defective products into a recycling process, thereby maintaining high-quality standards in continuous production.