Machine Performance Research Articles

As how artificial intelligence is revolutionizing endoscopy.

With incessant advances in information technology and its implications in all domains of our lives, artificial intelligence (AI) has emerged as a requirement for improved machine performance. This brings forth the query of how this can benefit endoscopists and improve both diagnostic and therapeutic endoscopy in each part of the gastrointestinal tract. Additionally, it also raises the question of the recent benefits and clinical usefulness of this new technology in daily endoscopic practice. There are two main categories of AI systems: computer-assisted detection (CADe) for lesion detection and computer-assisted diagnosis (CADx) for optical biopsy and lesion characterization. Quality assurance is the next step in the complete monitoring of high-quality colonoscopies. In all cases, computer-aided endoscopy is used, as the overall results rely on the physician. Video capsule endoscopy is a unique example in which a computer operates a device, stores multiple images, and performs an accurate diagnosis. While there are many expectations, we need to standardize and assess various software packages. It is important for healthcare providers to support this new development and make its use an obligation in daily clinical practice. In summary, AI represents a breakthrough in digestive endoscopy. Screening for gastric and colonic cancer detection should be improved, particularly outside expert centers. Prospective and multicenter trials are mandatory before introducing new software into clinical practice.

A Novel Design and Evaluation of a Five-phase Hybrid Excitation Partitioned Stator Flux-switching Machine

Background: In response to the need for improved performance in electric machines, this paper introduces and evaluates a novel hybrid excitation partitioned stator flux-switching (HEPSFS) machine. This design optimizes output torque while considering power density, torque density, and overall efficiency. Objective: The primary objective is to enhance electromagnetic torque production by minimizing flux leakage to the inner-stator core by creating an auxiliary air-gap in the inner-stator tooth. Additionally, a partitioned stator design is adopted to accommodate armature and field windings without space conflicts, allowing for increased windings and permanent magnets (PMs) to maximize torque density and flux regulation capability. Method: A comparative analysis is performed with a conventional HEPSFS (CHEPSFS) machine to evaluate the proposed design. Both machines share the same design dimensions and winding configuration to ensure a fair assessment. Finite Element Method (FEM) simulations using ANSYS Maxwell software are conducted to validate the results. Result: The analysis reveals that the proposed HEPSFS (PHEPSFS) machine outperforms the conventional counterpart. It exhibits higher torque output, torque density, power density, and efficiency while minimizing torque ripple. Moreover, at a current angle of 0 degrees, the PHEPSFS machine shows substantial percentage improvements compared to the CHEPSFS machine: a 285% increase in torque output, a 281.39% rise in power density, a 283.82% enhancement in torque density, and a 9.14% boost in efficiency. Furthermore, the PHEPSFS machine design reduces torque ripple by an impressive 59.63% compared to the CHEPSFS machine design. Conclusion: The study concludes that the PHEPSFS design effectively optimizes torque performance, making it a promising advancement in HEPSFS machines.

The Effect of Different Orchard Ground Conditions on the Performance of A Mechanical Hazelnut Harvesting Machine

In this study, the values of harvesting efficiency, field productivity, kernel productivity, kernel losses, and foreign material separation efficiency of hazelnut harvesting machine with mechanical harvesting unit were determined under different orchard ground conditions (ground preparation before harvesting (OG1) and without ground preparation (OG2)). Also, it was observed how these conditions affect the operation of the hazelnut harvesting machine. For this purpose, the harvesting efficiency, field productivity, kernel productivity and kernel losses of the hazelnut harvesting machine in OG1 and OG2 plots at 265.50 kg ha-1 orchard yield, 1600 mm working width and 1.60 m s-1 working velocity in two different orchard grounds were 96.05%, 90.15%; 8.624 h ha-1, 9.839 h ha-1; 0.116 ha h-1, 0.102 ha h-1; 778.72 kg h-1, 739.76 kg h-1; 3.95%, 9.85%, respectively. The hazelnut harvesting machine with a mechanical harvesting unit can work independently from the ground conditions and we can say that it is an alternative to other hazelnut harvesting machines. The data obtained from the study will help the decision-making process for the best selection and use by providing the necessary technical information about the functional aspects of the machine. Complete mechanization of hazelnut harvesting will lead to a decrease in labor requirements, thus increasing product profitability through a decrease in production cost. The presence of machines with high-performance characteristics in hazelnut harvesting mechanization will shorten the time the product stays on the ground and increase the quality of the harvested product.

An empirical approach to understand the role of emotions in code comprehension

Programming and cognitive skills are two pivotal abilities of programmers to maintain software products. First, this study included a systematic literature review on code comprehension, emotions, cognitive psychology, and belief-desire-intention domains to analyse various code comprehension monitoring techniques, performance metrics, and computational methodologies. Second, a case study is conducted to examine the influence of various emotional stages on programmers’ programming and cognitive skills while comprehending the software code. The categorization of the participants is done empirically based on their expertism level, and the same results are verified using various machine learning models and performance metrics.

Fruit recognition and classification based on tactile information of flexible hand

In the field of agricultural production, the sorting of agricultural products is a basic operation performed by robot manipulators. Agricultural products are fragile and easily damaged, and their shape, texture and size are different. In order to ensure grasping compliance and the integrity of agricultural products. In this study, firstly, a three-layer flexible tactile sensor was designed and fabricated. The performance of the sensor was tested. Three functions were used to fit the relationship between the sensor pressure and the output voltage, and the function with the best fitting degree was selected for sensor calibration. The sensor exhibits two kinds of sensitivity under the loading of 0 ∼ 4 N.When the applied pressure is 0 ∼ 2.75 N, the sensitivity is 1.21 V / N. When the applied pressure is 2.75 ∼ 4 N, the sensitivity is 0.24 V / N. Then, the sensor and the flexible gripper are combined to build a tactile information acquisition platform to collect the original data set of the tactile sequence generated when the flexible hand grabs the fruit, and the original data is preprocessed. Finally, we evaluated the performance of Support Vector Machine (SVM), Random Forest (RF), K-Nearest Neighbor (KNN), Naive Bayes (NB) and Neural Network (NN) in fruit classification. The results show that the RF classifier achieves the highest accuracy in the training and testing stages, which are 98.64% and 93.06%, respectively, and the accuracy of other classifiers ranges from 66.43% to 95.83%. Our work is helpful to the realization of robotic tactile perception and non-invasive grasping in the field of agriculture, and can be helpful to fruit picking, handling, sorting and other related fields.

Comparison of electromagnetic performance in MW class superconducting machines according to shielding and structures based on analytical method

This paper presents an analytical method for analyzing the electromagnetic performance of a superconducting (SC) machine according to the 10 MW shielding configuration and the presence or absence of an armature core. To establish the SC machine design process, an analytical method considers shielding conditions and armature core type is included. The presented analytical method derives the governing equations and general solutions for each region using Maxwell’s equations and electromagnetic field theory. Furthermore, it calculates the analytical solutions by applying appropriate boundary conditions. Additionally, the performance of actively and passively shielded, with the same size and shielding performance of SC machine is compared. The electromagnetic performance obtained through the analytical method is compared with finite element analysis to validate its accuracy. The accuracy of the presented analytical method can be utilized in various design analyzes, including initial design and optimal design.

Design of an Integrated Magnetorheological Fluid Brake Axial Flux Permanent Magnet Machine

This paper presents the design and performance of an integrated magnetorheological fluid brake axial flux permanent magnet (IMRFB-AFPM) machine with two switchable operation modes: rotation and brake modes while the machine has two kinds of windings: armature winding in axial stators and braking winding in radial stator. In rotation mode, this machine is equal to a conventional AFPM machine with high torque density. When switching to brake mode, MR fluid is excited by braking winding and applies large damping stress to the rotor to brake it. This paper illustrates the machine topology, operation principles, and design flow of the proposed machine. Then, this paper analyzes the torque generation mechanism in two modes and applies parameters optimization to improve the torque capability of each mode. Due to the independence of the magnetic flux path, the parameters optimization is divided into two parts: AFPM part and IMRFB part. After the optimization process, the electromagnetic performances of the optimal IMRFB-AFPM machine are analyzed by finite element (FE) analysis. Finally, a prototype machine with the optimal geometric parameters is manufactured and verified experimentally. The experiment results agree well with FE analysis results, validating the feasibility and practicability of the proposed design.

Armature MMF Reconfiguration Method of Six-Phase Integral-Slot PMSMs for Zero-Order Vibration Reduction Under Open-Circuit Faults

It is well known that the vibration performance of the permanent magnet synchronous machines (PMSMs) will deteriorate under the open-circuit fault operation. However, the cause of the vibration deterioration and corresponding methods to reduce the vibration are still unclear. This paper reveals the reason of the zero-order vibration deterioration for integral-slot six-phase PMSMs open-circuit fault operation. Furthermore, a magnetomotive force (MMF) reconfiguration method is proposed to suppress the fault-resulted zero-order vibration. The key is to eliminate the fundamental backward-rotating MMF, which contributes to the fault-resulted zero-order radial force under the open-circuit fault operation. With the aid of the response surface method, the analytical expressions of the optimal reconfigured current are derived considering all four open-circuit fault types. Compared with the conventional method, the fault-resulted zero-order radial force is greatly weakened by adopting the proposed method. Finally, the prototype of a six-phase 72-slot/12-pole PMSM is manufactured. The current and vibration tests are carried out to validate the theoretical analysis.

Effect of confining pressure on rock breaking by high-pressure waterjet-assisted TBM

High-pressure waterjet-assisted tunnel boring machine (WTBM) is an efficient method for improving the tunneling performance of a tunnel boring machine (TBM) and reducing the wear of its disc cutters in hard rock with high geostresses. Confining pressure directly affects the efficiency of rock breaking and the configuration of the disc cutters. In this study, we evaluated the effect of confining pressure on WTBM rock breaking by developing a self-designed and manufactured experimental system, including confining pressure loading, TBM disc-cutter penetration, and high-pressure waterjet. The macro fracture, acoustic emission (AE), peak normal force drop, and specific energy (SE) were analyzed for four different confining pressures (10, 20, 30, and 35 MPa). The results showed that the cutting depth of the waterjet increased linearly as the waterjet pressure increased and decreased with the gradual increase in the nozzle moving speed. The expansion and development of cracks formed rock debris, and the size of the rock fragments decreased with an increase in confining pressure. When the waterjet pressure was 280 MPa, the nozzle moving velocity was 800 mm/min and the kerf space was 75 mm, which indicated that the confining pressure, which was 23.16 MPa, minimized the cutting SE under this condition. However, regardless of the confining pressure, the maximum normal force of WTBM was less than that of a TBM, whereas the SE of WTBM was less than that of complete TBM cutting mode (CTCM). The average force drop and average drop rate of SE were approximately 25%, and 80%, respectively. The results of this study can inspire the design and mechanism of a TBM assisted by a high-pressure waterjet.

Mixed Eccentricity Fault Detection for Induction Motors Based on Time Synchronous Averaging of Vibration Signals

This paper presents a method based on vibration signals to diagnose rotor mixed eccentricity faults in three-phase squirrel cage induction motors (SCIMs). Rotor eccentricity is a typical fault in SCIMs that significantly affects the performance of electrical machines and results in unwanted vibrations. The time synchronous averaging (TSA) signal, which consists of the harmonics components generated by the fault, is obtained via the characteristic frequency of the eccentricity fault. TSA is decomposed into two signals: TSA-regular and TSA-difference, which are respectively similar to approximate and details of wavelet transform. Based on the fault index, which is the maximum FFT value of the TSA-difference signal, the healthy and faulty motors can be distinguished. The proposed approach is evaluated on an experimental test rig equipped with a 1.5 kW SCIM supplied directly from the power grid under various load conditions. The results illustrate the effectiveness of the proposed approach in detecting the rotor mixed eccentricity faults.

Comparative Analysis of LSTM Neural Network and SVM for USD Exchange Rate Prediction: A Study on Different Training Data Scenarios

Purpose: This paper aims to investigate and compare the performance of LSTM Neural Network and Support Vector Machines (SVM) in predicting the USD exchange rate using three different training data scenarios: 45%, 55%, and 75%. The study employs a dataset from the Indonesian Central Bureau of Statistics (BPS) for the period of January 1 to June 30, 2021, encompassing attributes USD Selling Rate.Methods: The methods involve implementing LSTM and SVM algorithms within the Python programming language using Google Colaboratory. Three distinct training data scenarios are explored to evaluate the models' robustness. Performance metrics, including Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and R-squared, are employed for evaluation.Result: Results reveal that LSTM demonstrates superior prediction accuracy compared to SVM across all scenarios, even though it incurs a longer training time. Notably, in the 75% training data scenario, LSTM achieves an MAE of 49.52, RMSE of 63.08, and R-squared of 0.37906, outperforming SVM with MAE of 138.33, RMSE of 161.58, and R-squared of 0.34277.Novelty: This study innovatively compares LSTM Neural Network and Support Vector Machines (SVM) for USD exchange rate prediction across different training scenarios (45%, 55%, and 75%). Unlike previous research focusing on individual models, this study systematically evaluates both methods, highlighting the nuanced balance between prediction accuracy and training time. The findings offer novel insights into LSTM and SVM applicability in currency forecasting, providing valuable guidance for researchers and practitioners in model selection based on specific predictive task requirements.

Evaluation of The Effectiveness of Die Casting Machines Using Overall Equipment Effectiveness (OEE)

PT YKK Zipco Indonesia is a manufacturing company that produces zipper components, namely chains and sliders. The manufacture of slider products goes through several departments, namely die casting, assembling, painting and plating. The process of making slider products begins with the die casting department which carries out the production process using 17 machines. The problem that exists in the die casting department is that the level of productivity is quite low, so an analysis of the effectiveness of the die casting machine is needed. The aim of this research is to evaluate the performance of the production process in order to increase the efficiency and effectiveness of the company as a whole. The method used in this research is overall equipment effectiveness (OEE) and six Big Losses. The Overall Equipment Effectiveness (OEE) method is used to measure the effectiveness of production process machine performance in manufacturing companies using the parameters availability, performance and quality. In OEE there are six big losses which are categorized into 3 main categories, namely quality loss, downtime loss and speed loss. Then an analysis was carried out using the Pareto diagram and fishbone diagram to find the root causes of the problems that occurred. The results of this research, namely the results of OEE calculations on the C – 07 Die Casting machine, obtained an average OEE value of 78.6%. Based on the six big losses calculation, breakdown losses occupy the highest value with a percentage of 23.1%, making it the losses that most influence the value of machine effectiveness.

Optimizing Support Vector Machine Performance for Parkinson's Disease Diagnosis Using GridSearchCV and PCA-Based Feature Extraction

Background: Parkinson's disease (PD) is a critical neurodegenerative disorder affecting the central nervous system and often causing impaired movement and cognitive function in patients. In addition, its diagnosis in the early stages requires a complex and time-consuming process because all existing tests such as electroencephalography or blood examinations lack effectiveness and accuracy. Several studies explored PD prediction using sound, with a specific focus on the development of classification models to enhance accuracy. The majority of these neglected crucial aspects including feature extraction and proper parameter tuning, leading to low accuracy. Objective: This study aims to optimize performance of voice-based PD prediction through feature extraction, with the goal of reducing data dimensions and improving model computational efficiency. Additionally, appropriate parameters will be selected for enhancement of the ability of the model to identify both PD cases and healthy individuals. Methods: The proposed new model applied an OpenML dataset comprising voice recordings from 31 individuals, namely 23 PD patients and 8 healthy participants. The experimental process included the initial use of the SVM algorithm, followed by implementing PCA for feature extraction to enhance machine learning accuracy. Subsequently, data balancing with SMOTE was conducted, and GridSearchCV was used to identify the best parameter combination based on the predicted model characteristics. Result: Evaluation of the proposed model showed an impressive accuracy of 97.44%, sensitivity of 100%, and specificity of 85.71%. This excellent result was achieved with a limited dataset and a 10-fold cross-validation tuning, rendering the model sensitive to the training data. Conclusion: This study successfully enhanced the prediction model accuracy through the SVM+PCA+GridSearchCV+CV method. However, future investigations should consider an appropriate number of folds for a small dataset, explore alternative cross-validation methods, and expand the dataset to enhance model generalizability. Keywords: GridSearchCV, Parkinson Disaese, SVM, PCA, SMOTE, Voice/Speech

Towards A Framework for Performance Management and Machine Learning in A Higher Education Institution

Performance management is a process that helps an organisation to manage its performance. Therefore, there are three stages of performance management such as coaching, corrective action, and then termination. A proper performance management process is very important for the development of a higher education institute. Apart from that, machine learning is another important process that is based on software technology. Therefore, machine learning helps to predict the outcomes of learning. There are a total of four types of algorithms of machine learning such as unsupervised, supervised, semi-supervised, and reinforcement. Furthermore, the use of performance management helps to enhance the productivity of the students of higher education institutions. In addition to that, the use of machine learning in higher education institutions is also helpful to enhance the productivity of the students. As both of the processes are efficient to gain knowledge about several things, therefore it helps to enhance the productivity of the students of higher education institutions.
 On the other hand, the purpose of this particular research study is to create a framework for machine learning and performance management in a higher education institution. Therefore, the framework is efficient and effective to understand the concept of research topics. Furthermore, the Framework for machine learning and performance management will help the students of higher education institutions to understand the impacts of these processes on their productivity. Apart from that, the researcher has used several types of methods and techniques for collecting and analysing all the data about the particular research topic. Thus, the researcher has adopted secondary methods for gathering more information and data about the research topic. Along with that, the researcher has used qualitative techniques for analysing all the data in this particular research study.

Advancing the Engineering Approach to Improving the Quality Cracking Efficiency of Palm Nut Crackiing Machine

A Palm Nut cracking machine with an improved beater configuration was developed to effectively crack Palm Nuts of various species and sizes. This research aim at improving the quality of the Palm kernel recovered at relatively low cost during Palm kernel oil production. Durable materials were acquired locally to fabricate the machine for ease of usage and maintenance, also to make it affordable for small and large scale processors. Basic features of the machine are; hopper, electric motor (prime mower), cracking chamber, cracking beater and discharge outlet. The design of the cracking drum and beater configuration was based on the impact force required to crack the Palm Nut which is a function of Palm Nut shear strength. A 5 hp electric motor was selected based on the power required to effectively operate the machine. The machine was tested with “Tenera” varieties, three nut sizes (14.5, 22.15 and 29.43mm) and five speeds (970, 1200, 1450, 1750 and 2430rpm). Result shows that the change in machine speed significantly (P<0.05) affects all the machine performance irrespective of the Palm Nut size and variety, which agrees with the report of several other researchers. The obtained optimum machine performance values are 14,874 nuts/h, 89.5%, 98% for the machine capacity, quality performance efficiency and cracking efficiency for Tenera variety. The best crop and machine parameter for the optimum performance of the Palm Nutcracker are 29.43 mm and 970 rpm, nut size and machine speed. It was concluded that the overall performance of this developed Palm Nut cracking beater was effective because it fell within the range of 80 to 98% efficiency.

AGB estimation using Sentinel-2 and Sentinel-1 datasets.

Climate change is one of the greatest threats recently, of which developing countries are facing most of the brunt. In the fight against climate change, forests can play an important role, since they hold a substantial amount of terrestrial carbon and can therefore affect the global carbon cycle. Deforestation, however, is a significant challenge. There are financial incentives that can help in halting deforestation by compensating developing countries for their efforts. They require however assessments which makes it essential for developing countries to regularly monitor their stocking. Based on the aforementioned, forest carbon stock assessment was conducted in Margalla Hills National Park i.e., Sub-tropical Chir Pine Forest (SCPF) and Sub-tropical Broadleaved Evergreen Forest (SBEF), in Pakistan combining field inventory with a remote-sensing-based approach using machine learning algorithms. Circular plots of a 20m radius were used for recording the data and Sentinel-2 (S2) and Sentinel-1 (S1) satellite data were used for estimating the Aboveground Biomass (AGB). The performances of Random Forests (RF) and Support Vector Machine (SVM) were explored. The AGB was higher for the SCPF. The RF performed better for SCPF, but SVM was better for SBEF. The free available satellite data in the form of S2 and S1 data offers an advantage for AGB estimations. The combination of S2 and S1 for future AGB studies in Pakistan is also recommended.

Performance enhancement of quantum Brayton engine via Bose-Einstein condensation.

Bose-Einstein condensation is a quintessential characteristic of Bose systems. We investigate the finite-time performance of an endoreversible quantum Brayton heat engine operating with an ideal Bose gas with a finite number of particles confined in a d-dimensional harmonic trap. The working medium of these engines may work in the condensation, noncondensation, and near-critical point regimes, respectively. We demonstrate that the existence of the phase transition during the cycle leads to enhanced engine performance by increasing power output and efficiencies corresponding to maximum power and maximum efficient power. We also show that the quantum engine working across the Bose-Einstein condensation in N-particle Bose gas outperforms an ensemble of independent single-particle heat engines. The difference in the machine performance can be explained in terms of the behavior of specific heat at constant pressure near the critical point regime.

A novel phase change material-based thermal management of electric machine windings enabled by additive manufacturing

While recent advances in additive manufacturing have provided immense opportunities for the development of next-generation electric machines, the machine thermal management has become one of the limiting factors to achieve high performances. Herein, a novel approach for the thermal management of electric machine windings under transient high-load conditions is proposed through the additive manufacturing of their magnetic cores with a thin-wall structure topology and filling their interstices with phase change materials (PCMs). The investigation initially focuses on reducing electromagnetic losses in the stator of an electric machine by changing its core topology from a bulk to a thin-wall structure. The effectiveness of PCM in curbing temperature rises within its winding is subsequently evaluated in scenarios where active cooling is absent or present. The analyses are performed by solving a set of coupled electromagnetic and heat transfer equations through a three-dimensional frequency-transient finite element analysis. The results demonstrate an increase of 74% in allowable duration before the safe temperature threshold is exceeded without active cooling. With active cooling, temperature rises are delayed by 104% at the early stages of operations. This offers a simple, low-cost, and efficient thermal management option for enhancing the performance of an electric machine and prolonging its working life.

Improving performance of extreme learning machine for classification challenges by modified firefly algorithm and validation on medical benchmark datasets

Improving performance of extreme learning machine for classification challenges by modified firefly algorithm and validation on medical benchmark datasets

Evaluation of Breaking and Deshelling Machine of Roasted Cocoa Beans

The manual cracking and separation of cocoa beans' husk result in low working productivity, a high percentage of broken beans, and the difficulty of separating cocoa nibs from the husk. This poses a challenge for both farmers and industrial players in cocoa bean management, leading to the development of a cocoa bean dehusking machine (desheller). This study was conducted to analyze the performance of the cocoa bean dehusking machine. The research involved motor speeds of 500, 700, and 900 rpm, combined with roasted cocoa bean grades AA, A, and B. The observed parameters included working capacity, yield, nib percentage, percentage of husk adhering to nibs, power transmission efficiency, and power requirements. The working capacity of the cocoa bean deshelling machine ranged from 17,413 to 41,481 kg/h, with yields between 73.83% and 80.83%. The nib percentage varied from 92.13% to 98.61%, while the percentage of husk adhering to nibs ranged from 1.08% to 6.92%. Power transmission efficiency was between 92.24% and 94.14%, and power requirements ranged from 601.33 to 645.33 watts. The best treatment in this study was found at a motor speed of 900 rpm with cocoa bean grade of AA. Keywords: Desheller, Nibs, Roasted cocoa beans, Shell, Yield