Machine Performance Research Articles

Survival games for humans and machines

Survival games can be described as video games where the player searches for food and treasures, while avoiding obstacles and hostile attacks. Ms.Pac-Man and Minecraft are two well-known examples. Currently there are AI models that outperform human players at Ms.Pac-Man, while AI models playing Minecraft above the human level has been a long-standing challenge. This paper concerns what we call pure survival games, which take place in previously unseen worlds containing only food, water, and obstacles. The challenge of the player is to navigate and survive in those worlds by continuously finding resources and avoiding obstacles. Arguably, animals need to master physical analogues of pure survival games in order to survive and reproduce. Here we begin to explore human and machine performance on pure survival games. We define two games called the Grid game and the Terrain game and two corresponding AI agents based on deep reinforcement learning: the Grid agent and the Terrain agent. We explore to what extent these agents can match human performance and how their performance is affected by variations in their perception, memory, and reward models. We find that (1) the Terrain agent performs above human level, while the Grid agent performs below human level; (2) the smell, touch, and interoception models contribute significantly to the performance of the Grid agent; (3) the memory model contributes significantly to the performance of the Grid agent; and (4) the performance of the Grid agent is relatively stable under three quite different reward signals, including one that rewards survival and nothing else.

Smart Sensor-Based Monitoring Technology for Machinery Fault Detection.

Rotary machines commonly use rolling element bearings to support rotation of the shafts. Most machine performance imperfections are related to bearing defects. Thus, reliable bearing condition monitoring systems are critically needed in industries to provide early warning of bearing fault so as to prevent machine performance degradation and reduce maintenance costs. The objective of this paper is to develop a smart monitoring system for real-time bearing fault detection and diagnostics. Firstly, a smart sensor-based data acquisition (DAQ) system is developed for wireless vibration signal collection. Secondly, a modified variational mode decomposition (MVMD) technique is proposed for nonstationary signal analysis and bearing fault detection. The proposed MVMD technique has several processing steps: (1) the signal is decomposed into a series of intrinsic mode functions (IMFs); (2) a correlation kurtosis method is suggested to choose the most representative IMFs and construct the analytical signal; (3) envelope spectrum analysis is performed to identify the representative features and to predict bearing fault. The effectiveness of the developed smart sensor DAQ system and the proposed MVMD technique is examined by systematic experimental tests.

A Novel Asymmetric Interior Permanent Magnet Machine with Auxiliary Flux Barriers

AbstractA novel asymmetric interior permanent magnet (AIPM) machine is proposed in this paper. The machine's rotor consists of asymmetric poles and auxiliary flux barriers. The torque ripple of the machine is weakened by the asymmetric design of the left and right sides of the magnetic poles. The magnetic‐field‐shifting (MFS) effect improves the electromagnetic torque after adding the auxiliary flux barrier to shift the magnetic axis. The influence of critical geometrical parameters on the electromagnetic performance of the machine is investigated under the condition that the stator and permanent magnet volume remain unchanged. The relevant geometrical parameters of the machine are optimized and designed through the improved Taguchi method. The performance of the AIPM machine and the conventional machine under no‐load and load conditions are further compared by simulation analysis with finite elements, verifying the increase in electromagnetic torque and the reduction in torque ripple. © 2024 Institute of Electrical Engineers of Japan and Wiley Periodicals LLC.

Online tracking of dynamically time-varying inertia using an enhanced SDFT-based estimation methodology

The overall motion performance of mechatronic machines depends heavily on proper knowledge of the machine’s characteristics, among which the inertia. Moreover, the inertia of most multi-body mechanisms, for example, reciprocating slider-crank mechanisms, varies as a function of the machine position, thereby challenging optimal control. Nevertheless, the inertia’s variation is sometimes not known accurately enough or changes over time due to, e.g. a production process or premature wear, forcing an online control/correction of the inertia profile. Therefore, earlier, the author developed a new computational-friendly online method based on a frequency-specific magnitude response to estimate the machine’s position-dependent load side inertia, assuming good knowledge of all other machine properties. Yet, to guarantee accuracy, the maximum machine speed during estimation had to be strongly reduced, resulting in an undesirable longer motion time. Therefore, in this work, the failure mechanism of the earlier proposed estimator is analysed and overcome by intelligently separating estimation and motion signals. As a result, the estimator is no longer limited by the machine’s motion speed but rather by a maximum in the inertia variation per signal excitation period and, thus, time. Moreover, given this limiting variation, a guideline was established to evaluate the new method’s estimation quality. Finally, both in simulation and on a physical machine, by taking advantage of the newly proposed method, the minimal required estimation time is reduced significantly (up to 50% on the machine) without diminishing the estimation accuracy.

Quantum Carnot thermal machines reexamined: Definition of efficiency and the effects of strong coupling.

Whether the strong coupling to thermal baths can improve the performance of quantum thermal machines remains an open issue under active debate. Here we revisit quantum thermal machines operating with the quasistatic Carnot cycle and aim to unveil the role of strong coupling in maximum efficiency. Our analysis builds upon definitions of excess work and heat derived from an exact formulation of the first law of thermodynamics for the working substance, which captures the non-Gibbsian thermal equilibrium state that emerges at strong couplings during quasistatic isothermal processes. These excess definitions differ from conventional ones by an energetic cost for maintaining the non-Gibbsian characteristics. With this distinction, we point out that one can introduce two different yet thermodynamically allowed definitions for efficiency of both the heat engine and refrigerator modes. We dub them excess and hybrid definitions, which differ in the way of defining the gain for the thermal machines at strong couplings by either just analyzing the energetics of the working substance or instead evaluating the performance from an external system upon which the thermal machine acts, respectively. We analytically demonstrate that the excess definition predicts that the Carnot limit remains the upper bound for both operation modes at strong couplings, whereas the hybrid one reveals that strong coupling can suppress the maximum efficiency rendering the Carnot limit unattainable. These seemingly incompatible predictions thus indicate that it is imperative to first gauge the definition for efficiency before elucidating the exact role of strong coupling, thereby shedding light on the ongoing investigation on strong-coupling quantum thermal machines.

A novel feature selection method based on quantum support vector machine

Feature selection is critical in machine learning to reduce dimensionality and improve model accuracy and efficiency. The exponential growth in feature space dimensionality for modern datasets directly results in ambiguous samples and redundant features, which can severely degrade classification accuracy. Quantum machine learning offers potential advantages for addressing this challenge. In this paper, we propose a novel method, quantum support vector machine feature selection (QSVMF), integrating quantum support vector machines with multi-objective genetic algorithm. QSVMF optimizes multiple simultaneous objectives: maximizing classification accuracy, minimizing selected features and quantum circuit costs, and reducing feature covariance. We apply QSVMF for feature selection on a breast cancer dataset, comparing the performance of QSVMF against classical approaches with the selected features. Experimental results show that QSVMF achieves superior performance. Furthermore, the Pareto front solutions of QSVMF enable analysis of accuracy versus feature set size trade-offs, identifying extremely sparse yet accurate feature subsets. We contextualize the biological relevance of the selected features in terms of known breast cancer biomarkers. This work highlights the potential of quantum-based feature selection to enhance machine learning efficiency and performance on complex real-world data.

Optimal Routing in Wireless Sensor Networks for Advancing IoT Efficiency and Sustainability using Enhanced Ant Colony Algorithm with machine learning approaches

This research study aims to investigate the incorporation of machine learning tools, such as Q-learning, Genetic Algorithms, Unsupervised Learning, and Ensemble Learning, into Enhanced Ant Colony Algorithm to assess the impacts of such incorporation on the WSN’s performance. Ten experimental trials were conducted on each to analyze the accuracy, precision, and F1 score results. It was observed that Q-learning achieves an average accuracy of 0.867; precision of 0.842; and F1 score of 0.854, making it highly adaptable and efficient in making routing decisions. The GA presented average accuracy of 0.833; precision of 0.812; and F1 score of 0.821 which show that the tool is highly robust in evolutionary optimization. Unsupervised learning machine performances indicate that the mean accuracy, precision, and F1 score for the model are 0.875, 0.856, and 0.865, respectively . As for ES with multi source models, the model showed the highest performance of 0.898, 0.882, and 0.891 in accuracy, precision, and F1 score, respectively . This study is thus very valuable in the backend regarding application of machine learning tools into routing optimization algorithms and efforts geared towards WSN efficiencies and sustainability..

Aerodynamic tunnel for tests of turbine annular cascades

Aerodynamic test rigs are necessary for experimental testing of turbomachines and investigation of possible ways to improve machine performance. Existing installations give higher losses and do not work efficiently at off-design operating modes. An operating part with an adjustable radial diffuser was designed in order to determine the characteristics of turbine annular cascades. Experimental studies and computational verifications showed satisfactory results at various operating modes. The regulated backwall of the radial diffuser ensured supersonic velocity values behind the cascade and overall stable operation in a wide range of Mach numbers up to 1.3 when using compressors of comparatively small capacity. The optimum positions of the regulated backwall were determined, which provided a deep vacuum behind the cascade, as well as 1.5 times Mach number increase compared to the turbine cascade without a diffuser. Changing the inlet channel geometry at supersonic modes leads to an increase in the diffuser efficiency. Additionally, it was determined that the use of the turbine vane cascade in the test rig flow path is not necessary during calculation studies, but instead an axisymmetric vaneless converging area can be applied and give satisfactory results as well as reduce the time spent on calculations. The computational model can be used to optimize the design of an aerodynamic tunnel outlet area.

Technological Prerequisites and Consequences of Ubiquitous Computing and Networking in Resurrecting Extinct Computers

The passage discusses the previous days of computing, highlighting the experiment of alternative processor designs, such as the Connection Machine (CM1). The CM1 was a unique architecture consisting of 65536 individual one-bit processors interconnected as a 12dimensional hyper-cube. Despite its innovative design, the machine faced challenges and eventually faded into obscurity. To preserve this piece of computing history, efforts have been made to develop a cycle accurate simulator of the Connection-Machine and create an RTL (Register Transfer Level) hardware description of its building block chip. These preservation steps are crucial in ensuring that the legacy of the Connection Machine is not forgotten. The evaluate of the Connection Machine performance yields mixed result. While it demonstrates impressive performance on certain tasks such as a breadth first search algorithm with a remarkably low cycle-per-element ratio, its limitations become apparent in other applications, particularly those in linear algebra. Factors like the 1 bit word size and latency of messages passing impose constraints on performance, especially in traditionally parallelizable applications. Overall, the passage underscores the importance of understanding and preserving the history of computing, including the exploration of alternative architectures like the Connection Machine, despite their eventual challenges and limitations.

Performance evaluation of a power-operated garlic (Allium sativum L.) bulb breaker for clove separation

Garlic (Allium Sativum L.) is a valuable root crop that can be utilized to season foods and is widely utilized in Ethiopia to treat many different kinds of diseases. The cloves are separated by hand for plantation and processing functions. This technique can be very exhausting and take a lot of time. To fill this gap, a garlic bulb-breaking machine was fabricated and tested with the clove variety grown in Holeta, Ethiopia. The major component of the machine is two rollers that revolve in opposing directions, and shearing the bulbs to separate the cloves. The performance test experiments were carried out in a full factorial design with feed rate as the first factor having three levels (3.7, 4.2, and 5.2 kg/min) and roller speed as a second factor with also three levels (276, 326, and 376 rpm). All tests were done at 66 % moisture content of garlic and 19 mm clearance between the breaking rollers. The interaction effect of the two factors shows an important difference (p < 0.05) in machine performance. The maximum breaking efficiency of (87.05 %) occurred at a feed rate (4.2 kg/min) and roller speed (326 rpm). Likewise, the maximum breaking capacity (306.98 kg/h) was recorded for the highest (5.2 kg/min) feed rate regardless of the 276 rpm roller speed. The minimum clumps of cloves (10.27 %) were obtained at combinations of 4.2 kg/min and 326 rpm. The lowest values of damaged cloves (1.79 %) and fuel consumption (5.61 ml/kg) were observed for the combination of the 3.7 kg/min with the 276.85 rpm whereas the maximum clove damage (2.29 %) was at the 5.2 kg/min feed rate combined with the maximum roller speeds (376 rpm). Therefore, the machine could be operated at the combination of 4.2 kg/min and 326 rpm for best performance in the majority of the parameters.

Comparison of CNN and SVM Methods on Web-based Skin Disease Classification Process

Skin, as the outermost layer of the body, is often in contact with bacteria, germs and viruses because of its most external position. According to statistics from the 2009 Indonesian Health Profile, skin illness is the third most common ailment seen in outpatient settings across the country's hospitals. Therefore, maintaining healthy skin is important because it protects the body's internal organs from injury and attack by pathogens. The development of image classification, such as the classification of skin diseases, has become a focus in the health sector. This research analyses the performance of Convolutional Neural Network (CNN) and Support Vector Machine (SVM) in web-based skin disease classification and overcomes the problem of imbalanced training data. With data augmentation and preprocess, this research improves data generalization and compares performance metrics such as Recall, Accuracy, and F1 Score. The results show that the average accuracy of CNN is 83.8%, while SVM reaches 81%. Although both models have high metrics for the normal class, other more complicated classes can only be handled by CNN with a value of more than 0.9. Apart from that, the CNN method also provides a higher Confidence Score than SVM, as well as a faster execution time. In conclusion, the CNN method is superior and recommended for skin disease classification based on web applications based on various performance test results.

辊式枝条捡拾机构运动学仿真与试验分析

Apple tree branches have the physical characteristics of high cellulose content and high elasticity, and the use of traditional soft straw pickers will miss a large number of branches. It is necessary to design a picking mechanism that adapts to the physical characteristics of fruit tree branches. In the treatment of branches in modern orchards, the picking mechanism is an important part of the picking device. The success rate of picking directly affects the processing performance of the whole machine. To improve the picking rate, the roller branch picking mechanism is studied. The trajectory of the roller picking and the stress state of the branches are analyzed, and five main factors affecting the picking effect are obtained, i.e. the position relationship between the rotation center of the picking roller and the feeding roller, inclination angle of the steel teeth, the effective working length, the speed and the forward speed of the machine. A mathematical model is established to obtain the static and dynamic motion trajectories of the roller picking mechanism are obtained by using Matlab. Taking the analysis results of influencing factors as the optimization goal, the picking trajectory of the mechanism is simulated to obtain a set of non-inferior solutions. A roller branch picker is manufactured according to the parameter values and tested in the field, and the picking rate can reach 91%.

Financial Crisis Prediction and Stock Market Analysis: A Systematic Review

Abstract: It is common known that attempting to foresee the movements of the stock market is a huge task that calls for a great lot of focus and concentration. Because of this, precisely predicting stock prices might potentially result in attractive rewards if the necessary decisions are made. This is the reason why this is the case. The non-stationary, noisy, and chaotic data that is accessible makes it difficult to generate correct forecasts about the stock market. This is because accurate predictions are difficult to produce. Because of this, it is difficult for investors to generate accurate forecasts in order to invest their money and earn a return from their investments. Various strategies are developed within the framework of the existing methodologies in order to forecast stock market movements. An overview of research articles arguing for different approaches is the goal of this study. In addition to being great academic publications, these research articles provide calculation methodologies, machine learning algorithms, performance factors, and other information. To address this recognized need, this study attempts to provide a comprehensive and current evaluation of the stock market forecasting approaches now in use. This research will include the categorization, analysis, and comparison of various approaches. In the end, the process of training and testing the model is evaluated using machine learning models. Based on the data, it is abundantly evident that logistic regression is better than any other approach that is presently being used.

Age and Gender Classification Using Convolutional Neural Network

Abstract: Now a days Age and gender are two crucial facial traits that influence social relationships. Human age and gender are determined by identifying facial images. This research focuses mostly on real-time applications like biometric verification and aging analysis. Age groups include child, young, adult, and old. Gender classification is the process of classifying males and females based on face images. CNN is used to classify people by their age and gender. CNN (Convolutional Neural Network) is used for analyzing visual data. CNN models are a superior type of image classification that, when compared to support vector machine performance on the dataset, where the UTK Face, Tuftes face dataset has 15171 photos, in order to increase the heterogeneity of the training and facial recognition on the dataset.

Development and optimization of a mechanized jackfruit processing unit for enhanced efficiency and commercial viability

AbstractThe jackfruit is the largest edible fruit but remains underutilized due to challenges such as sticky latex, labor‐intensive peeling/coring, and lack of mechanization. This study developed and evaluated a jackfruit peeling, coring, and cutting machine to enhance processing efficiency. Performance was modeled using response surface methodology (RSM) and artificial neural network (ANN). Three jackfruit sizes (small, medium, and large) and three machine speeds (90, 120, and 150 RPM) were evaluated for peeling time (26.1–50.3 s), peeling efficiency (71.6%–85.3%), coring time (15.5–29.9 s), coring efficiency (74.7%–96.0%), and bulb wastage (6.2%–17.6%). RSM showed high model adequacy (R2 ≥ 0.97) and ANN confirmed prediction reliability (R2 = 0.81–0.99; mean square error = 4.4–44.9). Increasing fruit size significantly increased peeling and coring times but decreased efficiencies. Machine speeds caused minor variations. Optimized conditions of 120 RPM fruit holder speed and 150 RPM corer speed gave maximum desirability (0.869). The machine had a payback period of 2 years and benefit–cost ratio of 2.32 versus 2.66 for manual peeling/coring. The mechanized jackfruit processing will promote enhanced utilization of this nutritious fruit.Practical applicationsThe mechanized jackfruit peeling‐coring‐cutting machine developed in this study has significant practical utility. By enabling efficient and rapid processing of jackfruits, the machine can help tap the underutilized potential of this highly nutritious and functionally beneficial fruit. The optimized machine parameters allow jackfruit processing industries to achieve higher throughput with reduced wastage, thereby boosting productivity and profits. Additionally, the mechanization facilitates value‐addition by enabling jackfruit utilization in various processed products like chips, flour, jam, etc. Further, the machine helps create livelihood opportunities in jackfruit value chains, as it reduces drudgery and enhances process efficiency as compared to manual methods. The simple fabrication and operation also enable adoption by farmer‐producer organizations, self‐help groups, and community‐based jackfruit processing enterprises. Overall, the mechanized solution provides an impetus for sustainable utilization of jackfruit, while also addressing issues like food loss, nutrition security, income support, and women empowerment. The practical insights on machine performance modeling using response surface methodology and artificial neural network approaches further facilitate quality improvements in equipment design.

Six Sigma Dalam Perspektif Akuntansi Manajemen: Peningkatan Manajemen Biaya Strategis dan Pengendalian Kualitas Produk

The background to this research is that companies that produce snacks often face challenges in managing ever-increasing operational costs and maintaining consistent product quality. In an effort to control increasing production costs, including raw material and labor costs, the company decided to implement Six Sigma as a quality management strategy. Companies face pressure to maintain competitive selling prices while controlling production costs. Variability in the quality of snack products often occurs, which can reduce consumer confidence. The research method uses qualitative and quantitative methods. The types of data used in this research include primary and secondary data, and the data collection methods applied include interviews, observation and documentation. The population that is the focus of the research is the snackproducts. The research sample was selected from a small portion of the population for further analysis. Data analysis was carried out using the Six Sigma method which consists of five stages: define, measure, analyze, improve and control (DMAIC), as well as linear regression analysis. The results of this research provide evidence that Six Sigma can be used as an effective tool to optimize strategic costs and improve product quality. Based on the analysis, the results obtainedare: 1. Machine. Continuous use of the machine results in decreased machine performance. 2. Employees. Suboptimal work results in the product not meeting quality standards. Therefore, this research makes an important contribution in deepening understanding of the application of Six Sigma to achieve cost management goals and improve product quality.

Performance Evaluation of Half-Feed Rice Combine Harvester

Rice (Oryza sativa) is one of the most important cereal grains cultivated in an area of 165 million hectares with approximately 756.7 million metric tons of production in the world. In 2019, Pakistan’s area under rice cultivation was about 2.9 million hectares, with 7.5 million tons yield. Rice-wheat cropping system is the most famous, especially in Punjab, Pakistan. Harvesting is presently conducted through manual labor or with the utilization of outdated models of combined harvesters with huge grain quality and quantity losses. Imported half-feed rice combine harvester was introduced and an experiment was planned to evaluate their feasibility. The performance was evaluated at three levels of forward speed (3, 4, and 5 km/h) and cutter bar heights (12, 16, and 20 cm) during the harvesting season of 2021 in the district Sheikhupura, Punjab. The machine performance was based on header loss, effective field capacity, broken grains percentage, fuel consumption, and field efficiency. The collected data was analyzed at a 5% level of probability by randomized complete block design (RCBD). The statistical analysis revealed that the machine performed better at the speed S2 (4 km/h) and cutter bar height H2 (16 cm) with the maximum EFC (0.55 ha/h) and Field Efficiency (75.3 %) as well as minimum Grain Losses (24.7 kg/ha) and Grain Breakage (14.2 kg/ha) in standing crop condition. Therefore, this machine is recommended to farmers due to its higher EFC and Field Efficiency as well as lower Grain Losses and Grain Breakage as compared to the conventional methods and obsolete machinery.

Analisis Kinerja Mesin CNC Milling 3 Axis pada Pembuatan Pipa Jet Oil

The study evaluated the performance of a 3-axis CNC milling machine in the production of jet oil pipes with a focus on achieving a high level of precision. Through variation of cutting parameters and feeding speed, the machine succeeded in reaching the industry standard for jet oil pipe production. Optimization of parameters improved production efficiency, demonstrated by results that achieved the desired precision tolerance. Cutting tool wear analysis provides insight into machine performance and possible repair actions. This research confirms the potential of 3 axis CNC milling machines in addressing the challenge of high-precision jet oil pipe production, contributing to the development of CNC Milling technology in the context of the oil and gas industry.

IMPLEMENTATION OF RELIABILITY CENTERED MAINTENANCE (RCM) II IN PACKAGING INDUSTRY PRODUCTION MACHINERY MAINTENANCE ACTIVITIES

Along with the increasing need for productivity and the use of high technology in the form of production machines and factories, the need for maintenance functions is also increasing. At PT. Weiss Tech, a packaging machine manufacturer, has problems mainly related to wire cut machine malfunctions which cause interruptions and delays in the production process and reduce machine performance. In overcoming these problems in this study, the Reliability Centered Maintenance (RCM) II method from Failure Modes and Effect Analyze (FMEA) was used. RCM II is one of the methods used to determine which components are due for repairs, while FMEA is defined as a method for identifying the root cause of engine failure. From the results of calculations using FMEA and RCM II, the results of the maintenance interval for the Electromotor component (electric motor) with a maintenance interval of 20 hours, for the Lower and upper nozzle components (upper and lower nozzles) with a maintenance interval of 181 hours, and for the Roller component (drive roller) ) with a treatment interval of 177 hours

Accuracy of cone-beam computed tomography in imaging the components of the periodontal phenotype.

The components and dimensions of the periodontal and peri-implant phenotype have a high relevance in contemporary dental research and should be taken into consideration in the decision-making process in the management of a variety of clinical scenarios to optimize the outcomes of therapy. Various assessment methods for quantifying and classifying the phenotypical dimensions have emerged and developed in recent decades. Nevertheless, the use of cone-beam computed tomography (CBCT) scans remains the most commonly used approach worldwide. However, the accuracy to adequately imaging and measuring the dimensions of the hard and soft tissue components around teeth may represent a significant challenge in different clinical scenarios due to factors such as the age of the patient and motion during the scan, presence of metallic artifacts causing streaks and gray-value distortion, overlapping of soft tissue structures, machine performance, file processing, and small voxel size among others. These factors pose a particular challenge when tiny structures are under investigation, for example, the buccal/lingual bony or soft tissue layer of lower/upper incisors. Therefore, this review addresses the underlying technical information of the use of CBCT scans, and suggests some recommendations on the utilization of this method of assessment to optimally use it despite its' system-inherent limitations.