This paper presents a deep neural network (DNN)-embedded mixed-integer linear programming (MILP) model for fault prediction and production optimization in tablet pressing machines. The DNN predicts the probability of failures during the tablet pressing process by analyzing key operational parameters such as pressure, temperature, humidity, speed, vibration, and number of maintenance cycles. The MILP model optimizes the temperature and humidity settings, production schedules, and maintenance planning to maximize total profit while minimizing penalties for fault pressing, energy consumption, and maintenance costs. To integrate DNN into the MILP framework, Big-M constraints are applied to linearize the Rectified Linear Unit (ReLU) activation functions, ensuring solvability and global optimality of the optimization problem. A case study using the Kaggle dataset demonstrates the model’s ability to dynamically adjust production and maintenance schedules, enhancing profitability and resource utilization under fluctuating electricity prices. Sensitivity analyses further highlight the model’s robustness to variations in maintenance and energy costs, striking an effective balance between cost efficiency and production quality, which makes it a promising solution for intelligent scheduling and optimization in complex manufacturing environments.
Engineering machinery, tools, and implements, Technological innovations. Automation
Heart disease is the leading cause of death across the world. However, such an early prediction of heart attacks can save lives if clinical data are used to predict it accurately. For this, we use four machine learning models: Naive Bayes, Decision Tree, Random Forest and K-Nearest Neighbors (KNN) to predict heart attacks from the data of the patients. Models developed achieved an average accuracy of 65.08%; however, this paper explores the performance of these models in real world healthcare applications. Our focus is on improving model performance by improving the quality of the data, the features and hyperparameter tuning. Future directions indicate combining deep learning techniques and larger dataset for more accurate prediction.
Mohammad Rajabi, Mohsen Hajibabaei, Massoud Tabesh
et al.
In this study, a graph-based method is implemented for sensor placement in a water distribution network (WDN) instead of using a hydraulic model. The proposed methodology determines the pressure sensors’ location based on the node betweenness centrality of nodes from their source, considering the WDN topology and assigning hydraulic-inspired edge weights. Furthermore, the Non-dominated Sorting Genetic Algorithm (NSGA-II) determines the end node of the WDN’s critical paths for sensor placement to maximize monitoring network efficiency to calibrate the model and avoid additional data collection. For different numbers of sensors, the NSGA-II algorithm is implemented 10 times and the final Pareto front is determined. The graph-based approach reduces the sensor placement problem complexity to an acceptable level and can be implemented as a surrogate approach for hydraulic-based sensor placement.
In this work, we describe the fabrication of paper-based aptasensing devices for ampicillin determination that rely on the salt-induced aggregation of gold nanoparticles (AuNPs) in the presence of the target. Circular paper-based devices were created on paper via pen-plotting (using water-repellent ink to create hydrophobic barriers) and modified with NaCl. The sample was incubated with an ampicillin aptamer and AuNPs and was added to the assay zones of the paper-based devices. In the absence of ampicillin, the aptamer prevented the aggregation of the AuNPs, and the assay zones remained red. When ampicillin was present, it selectively bound with the aptamer and the AuNP aggregate, producing a purple color. The color of the assay zones was monitored via a smartphone, and the color graduation was related to the ampicillin concentration in the sample. Different experimental parameters (type of paper, concentration of reagents) were investigated, and the analytical features of the method for the determination of ampicillin were established.
Phase loss is a typical problem in the optical domain, and optical detectors only measure the amplitude distribution of a signal without its phase. However, an optimal phase is desired in a variety of practical applications, such as optical metrology, nondestructive testing, and quantitative microscopy. Several methods have been proposed to quantitatively measure phase, among which interferometry is one of the most commonly used. An intensity interferometer has also been used to recover phase and enhance the phase difference measurement via the intensity correlation. In this paper, we present and examine another technique based on the Stokes correlation for enhancing phase measurement by a factor of two. The enhancement in phase measurement is accomplished through an evaluation of the correlation between two points of Stokes fluctuations of randomly scattered light and by recovering the enhanced phase of the object by using three-step phase shifting along with the Stokes correlations. This technique is expected to be useful for imaging and the experimental measurement of the phase of a weak signal.
Shopping malls may be considered as controversial structures since they sometimes fail to comply with the expectations of the project stakeholders throughout the project life cycle. New mall projects often attract the attention of people since such a structure has a potential to reshape the neighborhood it is located in; however, the impact is usually negative. On the other hand, the parties involved in mall projects may be subject to criticism from both the public and the industry during the design, construction, and operation. In this study we conducted semi-structured interviews with five managers of an international company that provides real estate services worldwide, and mainly focuses on managing shopping centers within the context of Turkiye. During the interviews, we collected insights on shopping mall design and criteria that have an impact on the operational success or failure. We analyzed the interview data to understand the shopping mall design requirements from the experts’ perspectives. We summarized our investigation under three main categories as location, shop and brand mix, and design. Analyzed data indicates that the requirements and use of shopping malls evolve and change over time. The change is driven by things such as changing habits and expectations of the users and new marketing approaches. Understanding such changes is essential for designers and investors to propose new design approaches and space compositions in order to be able to adapt to the changes. Through our analysis of the collected data, we provided insights on requirements and new trends that affect the design of malls. As further explained in this paper, our analysis indicates a number of important topics during design such as the need to design to fit ever-changing spatial needs, providing feel-good environment for users, correct placement of spaces and stores related to each other, designing circulation that supports commercial activities, and designing with a consideration of operation and maintenance. According to the collected data, the trend of shopping mall design is towards integration of hybrid uses, free forms, more open spaces, increased emphasis on gastronomy, and enabling socializing while leveraging technology and being more sustainable.
Christensen derived solutions of macroscopic elastic constants of composite materials containing randomly oriented fibers (Christensen, 2005). In this study, by extending Christensen’s method, the analysis of macroscopic physical properties of a composite material containing ellipsoidal reinforcements oriented randomly will be performed. Macroscopic elastic constants, thermal expansion coefficients and dielectric constants of the composite material could be expressed explicitly by using solutions for ellipsoidal reinforcement oriented unidirectionally. As a result of calculations for various ellipsoidal shapes of reinforcement by using derived solutions, it was confirmed that these analytical results of macroscopic physical properties exist between the upper and lower bounds of Hashin et al. Furthermore, by comparing the present result with the result of solution based on Mori-Tanaka’s theory and the experimental result, the validity and applicable range of the analytical solutions were examined.
Mechanical engineering and machinery, Engineering machinery, tools, and implements
Pei-Cheng Cheng, Yuan-Chung Lin, Min-Siou Lin
et al.
Weathered petroleum-contaminated soil was treated with <i>Vetiveria zizanioides</i> (Vetiver) and <i>Cymbopogon nardus</i> (Lemongrasss) to investigate the efficiency of phytoremediation. The initial total petroleum hydrocarbon (TPH) concentration of soil was 3000−8000 mg/kg, and after 6 months, the TPH concentrations were degraded by 50−75% under the action of soil native microbial. Planting vetiver and lemongrass stabilized soil pH and electrical conductivity, and it accelerated the decomposition of TPH in soil. Planting vetiver showed a better effect. After 6 months of planting, the TPH decomposition efficiency reached about 90%, and most of the easily decomposed TPH has been decomposed. The results of rhizosphere soil microbiota analysis also showed that planting vetiver increased the abundance of soil microbiota.
Transfer learning has not been widely explored with time series. However, it could boost the application and performance of deep learning models for predicting macroeconomic time series with few observations, like monthly variables. In this study, we propose to generate a forecast of five macroeconomic variables using deep learning and transfer learning. The models were evaluated with cross-validation on a rolling basis and the metric MAPE. According to the results, deep learning models with transfer learning tend to perform better than deep learning models without transfer learning and other machine learning models. The difference between statistical models and transfer learning models tends to be small. Although, in some series, the statistical models had a slight advantage in terms of the performance metric, the results are promising for the application of transfer learning to macroeconomic time series.
Due to the COVID-19 pandemic, courses for all ages in many countries moved online. The ability to use information technology fluently for learning has become a vital issue. Whether students can develop computational thinking (CT) literacy in online or offline learning environments is investigated. Two web games, Rummikub and Robozzle, are applied to teach computational thinking through Google Meet, Google Classroom, and offline live teaching. The results indicate that offline training activities are more appropriate for middle school students.
The process of forming a doped Tin oxide (FTO) nano fluoride layer was made using Tin Chloride (SNCL2) with Ammonium Fluoride (NH4F) mixing process using a magnetic stirrer at room temperature (28oC). The solvent liquid uses 99% ethanol. Both of these solutions are mixing and finally get the fluorinated doped fluorine Tin. The deposition method of the nanolayer uses the pyrolysis process to produce FTO substrates. This research focused on the production of materials that have transparent properties and have conductivity values. It based on the requirements of work solar cells to work. The process of measuring transparency uses an absorbance measurement tool. Measurement of conductivity using a conductivity meter with a 4-point circular Probe method used in this study was divided into four variations, including starting from 400, 425, 450, 475, 500 degrees Celsius. From this method, the best results were obtained at a temperature of 475 degrees Celsius with an average value of 25 Ω / cm and the highest percentage of transmittance.
Shota HASUNUMA, Asuka HATANO, Satoshi IZUMI
et al.
In this study, the effect of machined surface layer on residual stress relaxation was investigated. In previous study, low cycle fatigue strength was affected by residual stress. However, residual stress relaxation was complex because local plastic strain occurred by stress near yield stress. Also, machined surface layer affect the yield stress. Therefore, machined surface layer was modeled using the crystal plasticity model, i.e. plasticity model based on crystallographic deformation mechanics. To describe the microstructure of plastic deformation layer, initial dislocation density and back stress near surface were changed. To describe the microstructure of fine grained layer, grain size near surface was changed. Residual stress relaxation was simulated by crystal plasticity finite element method. Three types of machined surface layers were modeled. Two kind of strain amplitude condition was simulated. In simulation results, local plastic strain was occurred under global elastic condition. Residual stress after cyclic load was different from machined surface conditions under low strain loading. Residual stress was largely relaxed in all cases under high strain loading. Comparing fatigue life of experimental results, simulation results were thought to be valid. Therefore, residual stress relaxation is able to be predicted using this model. Hardening in plastic deformation layer prevents yield by tensile load. However, plastic strain was occurred in plastic deformation under compression load. On the other hand, fine grain layer prevent yield by not only tensile but also compression.
Mechanical engineering and machinery, Engineering machinery, tools, and implements
Although assembly line is widely used for several decades since it appears during the Industrial Revolution, nowadays, it still has the vitality, especially in the developing countries such as China, where labor-intensive enterprise is still the mainstay industry. Assembly line has its advantages for reducing costs and production time. However, laborer is the main factor of production speed in such a labor-intensive enterprise. Because of the various working capacity of worker, one work process may delay or idle, and this will influence processes. This unforeseeable consecutive delay of process may lead to the postponing of whole manufacturing production. In order to minimize the risk, the assignment of the workers, especially untrained worker is focused on. In previous researches, rules of optimal worker assignment with two kinds of workers, which are distinguished by the capacity of processing, were proposed when minor untrained workers are less than four people. In this paper, we deal with the rules under this LCMwMP (limited-cycled model with multiple periods) model without concerning the number of minor untrained workers. Additionally, some rules of minor well-trained workers assignment optimization are researched by numerical analyses.
Engineering machinery, tools, and implements, Mechanical engineering and machinery
Applications of fiber reinforced plastics have been expanding due to improvement of not only fuel efficiency but also the motion performance of some recent vehicles. Especially, the demand for injection-molded fiber reinforced thermoplastics is expected to increase because of their superior moldability, productivity and recyclability. In this study, the influence the fiber diameter has on the impact tensile properties of long glass-fiber reinforced polyamide (GF/PA) is investigated using the split Hopkinson pressure bar method. Prior to the tensile tests, an investigation of the fiber-orientation distribution was conducted in order to cut out specimens with the same fiber orientation angle from the injection molded plate. Two types of specimens, referred to as specimens with high- and low orientation angle, were manufactured using glass fibers with average diameters of 13, 17, 23 μm. In the tensile test, the GF/PA with smallest fiber diameter showed the highest tensile strength and the most significant strain rate dependency on the strength. These effects were more significant for the specimens with high orientation angle. From SEM observations on the fracture surface and an average fiber length measurement, it was observed that the interfacial fracture and the fiber breakage were dominant failure modes under the considered tensile loading conditions. It was suggested that decreasing the stress acting on the fiber/matrix interface by reducing the fiber diameter affected the improvement of the GF/PA strength. Using the modified linear rule of mixtures, the tensile strength was predicted. The predictions showed good agreement with experimental results. Therefore, it is believed that the decrease of critical fiber length is the reason that the impact tensile properties are higher for the samples with smaller fiber diameter.
Mechanical engineering and machinery, Engineering machinery, tools, and implements
The aim of this paper is to explore the model calibration method consisting of the effective design of experiment (DoE) and the model selection for DoE. D-optimality is exploited as the cost function, and the optimal experiment design for the model is calculated by Fedorov's exchange method. An actual implementation example for air-mass flow model of gasoline engines is carried out. The model is chosen in the fashion of minimum cAIC criteria with the preliminary experiment for the purpose of the application of DoE. The experiment result with a full-scale engine test bench is validated to confirm that the proposed method can improve the accuracy of the calibrated model. The comparison of the proposed method with the conventional mesh experiment design by the calibration result is shown.
Mechanical engineering and machinery, Engineering machinery, tools, and implements
A prototype-rotary creaser was experimentally applied to an AB double-wall corrugated fiberboard to reveal creasing characteristics of the corrugated fiberboard and mechanical factors on failures of its height wise crease. Through this work, the followings were obtained. (1) There are appropriate combinations of pre-creaser gap and main-creaser gap for restricting the failure occurrences in the inside liner; (2) The pre-stage creasing for crushing corrugated medium was severely necessary for reducing the failures of the inside liner and performing the high-precision positionment for bending; (3) Dependency of water content and feed velocity on the failures of the inside liner was revealed.
Engineering machinery, tools, and implements, Mechanical engineering and machinery