Powerful Machine Research Articles

Design and Optimisation of a 5 MW Permanent Magnet Vernier Motor for Podded Ship Propulsion

The evolution of electric propulsion systems in the maritime sector has been influenced significantly by technological advancements in power electronics and machine design. Traditionally, these systems have employed surface-mounted permanent magnet synchronous motors (PMSMs) in podded configurations. However, the advent of permanent magnet Vernier motors (PMVMs), which leverage magnetic gearing effects, presents a novel approach with promising potential. This study conducts a comparative analysis between PMVMs and conventional PMSMs at a power level of 5 MW for podded ship propulsion, with a particular focus on the impact of gear ratios (Gr). An objective function was developed that integrates motor dimension constraints and the power factor (PF), a critical yet frequently neglected parameter in existing research. The findings indicate that PMVMs with lower Gr have lower mass and cost compared to those with higher Gr and traditional PMSMs, at a PF level of 0.7, which is high for Vernier machines. Moreover, PMVMs with lower Gr achieve efficiencies exceeding 99%, outperforming both their higher Gr counterparts and conventional PMSMs. The superior performance of PMVMs is attributed to lower current density and reduced copper loss, which contribute to their enhanced thermal performance. These details are elaborated on further in the paper. Consequently, these findings suggest that PMVMs with lower Gr are particularly well suited for high-power maritime propulsion applications, offering advantages in terms of compactness, efficiency (EF), cost-effectiveness, and thermal performance.

Revolutionizing the used car market: Predicting prices with XGBoost

In contemporary dynamic automobile industry, informed decision-making is crucial for success. Accurate sales predictions are essential for optimizing operations and resource allocation in the used car market. This article explores the application of machine learning, specifically the eXtreme Gradient Boosting(XGBoost) algorithm, in predicting used car prices in the UK. The dataset consists of over 110,000 data points from various brands, including features like model, year, mileage, and more. Data preprocessing, including outlier removal and feature scaling, is performed to prepare the dataset. XGBoost, a powerful machine learning algorithm, is selected for price prediction and compared with traditional regression models. The results show that eXtreme Gradient Boosting(XGBoost) outperforms other models in terms of R2 score, Mean Absolute Error, and Mean Square Error. Its accuracy and efficiency make it a valuable tool for both buyers and sellers in the used car market. However, challenges such as data quality, feature engineering complexity, and model interpretability remain. Future research directions include improving data quality, exploring advanced feature engineering techniques, and integrating external data sources. This study highlights the potential of machine learning in enhancing decision-making in the dynamic used car market.

XLMR4MD: New Vietnamese dataset and framework for detecting the consistency of description and permission in Android applications using large language models

Google Play and other application marketplaces have various Android applications and metadata. Among these, description information and privacy policy help explain the application's functionality. They also describe the permission of the application, especially those related to sensitive information. Detecting the inconsistency between the description of the application and privacy information and the permission extracted in the application's source code helps users decide whether to install and use the application. In this research, we propose a new method based on a pre-trained language model to detect inconsistencies between the permission extracted from the description application and privacy policy and the permission extracted from the application's source code (file APK). Related works focus on models of large-scale datasets, especially for resource-rich languages such as English. However, a language with low resources, like Vietnamese, needs more datasets for the task. To solve this problem, we propose the ViDPApp dataset (Description and Privacy Policy of Applications on Vietnamese domains), a high-quality dataset that humans manually annotate with 12,000+ sentences with an inter-annotator agreement (IAA) of over 85%. In addition, we proposed XLMR4MD, a new framework using large language models, outperforming powerful machine models (LSTM, Bi-GRU-LSTM-CNN, WikiBERT, DistilBERT, mBERT, and PhoBERT) and achieving the best with 84.04% F1 score in detecting inconsistencies between Android application permission and description. This framework can be fine-tuned for 100 languages, which benefits low-resource languages like Vietnamese. The dataset is available for research purposes.

Predicting the Displacement Variation of Rehabilitated Foundation of Onshore Wind Turbines Using Machine Learning Models

The rehabilitation of wind turbine foundations after damage is increasingly common. However, limited research exists on the deformation of wind turbine foundations after rehabilitation. Artificial intelligence methods can be used to analyze future deformation state and predict post-rehabilitation deformation of foundations. This paper focuses on analyzing the stability of damaged wind turbine foundations after rehabilitation, as well as establishing and evaluating machine learning models. Specifically, Decision Tree (DT), Extreme Gradient Boosting (XGB), Support Vector Regression (SVR), and Long Short-Term Memory Network (LSTM) models are utilized to predict the vertical displacement of the rehabilitated foundation. Hence, the stability of the rehabilitated foundation is discussed in correlation with the measured wind speed, based on the foundation vertical displacement data. During the development of the machine learning model, the most suitable combination of hyperparameters is determined. The prediction performance of the SVR and LSTM models, which exhibit good performance, is compared to further evaluate their effectiveness. Furthermore, the models are analyzed and validated. The results indicate that the vertical displacements of the rehabilitated foundations gradually get close to a state of steady fluctuation over time. The SVR model is identified as the most effective in predicting the vertical displacements of wind turbine foundations after rehabilitation. This study aims to analyze and predict the vertical displacement of wind turbine foundations after rehabilitation based on extensive field monitoring data and powerful machine learning models.

The swimming defect caused by the absence of the transcriptional regulator LdtR in Sinorhizobium meliloti is restored by mutations in the motility genes motA and motS.

The flagellar motor is a powerful macromolecular machine used to propel bacteria through various environments. We determined that flagellar motility of the alpha-proteobacterium Sinorhizobium meliloti is nearly abolished in the absence of the transcriptional regulator LdtR, known to influence peptidoglycan remodeling and stress response. LdtR does not regulate motility gene transcription. Remarkably, the motility defects of the ΔldtR mutant can be restored by secondary mutations in the motility gene motA or a previously uncharacterized gene in the flagellar regulon, which we named motS. MotS is not essential for S. meliloti motility and may serve an accessory role in flagellar motor function. Structural modeling predicts that MotS comprised an N-terminal transmembrane segment, a long-disordered region, and a conserved β-sandwich domain. The C terminus of MotS is localized in the periplasm. Genetics based substitution of MotA with MotAG12S also restored the ΔldtR motility defect. The MotAG12S variant protein features a local polarity shift at the periphery of the MotAB stator units. We propose that MotS may be required for optimal alignment of stators in wild-type flagellar motors but becomes detrimental in cells with altered peptidoglycan. Similarly, the polarity shift in stator units composed of MotB/MotAG12S might stabilize its interaction with altered peptidoglycan.

How to solve a binary cubic equation in integers

AbstractGiven any polynomial in two variables of degree at most three with rational integer coefficients, we obtain a new search bound to decide effectively if it has a zero with rational integer coefficients. On the way we encounter a natural problem of estimating singular points. We solve it using elementary invariant theory but an optimal solution would seem to be far from easy even using the full power of the standard Height Machine.

Features of the implementation of control (supervisory) activities in the field of the technical condition of self-propelled machines and other types of equipment by the State Technical Supervision bodies of the Russian Federation

The year 2024 is a natural continuation of the reform of control (supervisory) activities, which began in 2020 in the Russian Federation. The concept of improving control (supervision) activities adopted by the Ministry of Economic Development until 2026 defined the final "philosophy" of control (supervision). It immediately became clear that the implementation of certain control (supervisory) functions is not possible without the reform of the activities of individual executive authorities performing these functions. The subject of our research is the specifics of the control (supervisory) activities of the State Technical Supervision bodies of the Russian Federation in 2024 under the conditions of the moratorium and the development of the concept of improving control (supervisory) activities until 2026. Our article aims to propose approaches that allow for the integration of supervision of self-propelled vehicles into a new reality aimed at reducing the pressure of the state, as a power machine, on economic entities. In addition, the subject of the study also includes the definition of generally applicable signs, tasks and principles of control (supervision). The definition of similarities and differences between the concepts of "control" and "supervision" does not remain without attention of the author. The scientific novelty of the study lies in the proposed ways to change the current activities of Gostekhnadzor bodies related to the implementation of control (supervision) in the field of the technical condition of self-propelled machines and other types of equipment, namely, amendments to the current legislation of the Russian Federation regulating this area. An important conclusion of the study should be the identification of the inapplicability of a risk-based approach to all types of control (supervision). In addition, we propose a structure of general requirements for the organization and supervision of self-propelled vehicles, as well as a change in the current version of Article 9.3 of the Administrative Code of the Russian Federation, corresponding to new realities and allowing, within the framework of a "permanent raid", to bring to administrative responsibility drivers of self-propelled vehicles that violate mandatory requirements in the field of their technical condition.

EXPERIMENTAL EXPLORATIONS WITH DIGITAL FABRICATION FOR PREFABRICATED CONSTRUCTION SYSTEMS

Digital fabrication tools are powerful machines that have opened a new mindset in the whole construction process and have brought a perfect scene for experimental explorations in the prefabricated construction industry. However, it is still an outlier in the Ecuadorian construction industry where it is uncommon to have industrialized techniques and digital manufacturing machinery. Consequently, academia should promote its use by learning, teaching, and experimenting with these tools. Prefabricated construction enhances technology, logistics, assembly methods, and resource optimization. Combining these two leading techniques will reshape the construction process and make a more efficient industry. Digital prefabrication utilizes advanced technology to improve quality, lower costs, and rapidly test new ideas. This article describes the processes and the experimental approach used in two case studies for building concrete prefabricated pieces with digital manufacturing. Concrete was chosen as the material for the research due to its high demand in the local industry. The objective was to prefabricate items, that could work as an entire system, with a high level of optimization for sustainable construction that achieves scale and repeatability. Lastly, it is significant to mention the lack of local references in this area; therefore, these tests explore the capacity of using digital fabrication to build precast concrete panels to create prototypes that will serve as starting points for further research. Keywords: Digital Manufacturing, Prefabrication, Precast Concrete, Experimental explorations, CNC Fabrication, Expanded Polystyrene (EPS), Concrete panel, Rapid Prototyping.

Steps towards a therapeutic artificial intelligence

Whether artificial intelligence might benefit human well-being in every sense is an open question. I consider it in the following essay, first putting to one side standard accounts of ‘official AI’, then deriving an ‘unofficial’ counterpart from the evidence of newspaper accounts and magazine features from ca. 1945–1965. Unsurprisingly, these demonstrate a bending of artificial intelligence to military and industrial purposes, hence the enormity of the impediment to therapeutic applications, but at the same time the evidence leaves no doubt as to the imaginative power of smart machines. Contemporary commentary is brought to bear to move from intimations of a dark future to possibilities for constructing a healthy practice. I conclude with two quite different 21st century examples of a way towards it.

Improving Steady State Accuracy in Field-Weakened Six-Phase Induction Machines with Integrator and Modulated Predictive Control

Finite-control-set model predictive control techniques are considered an exciting option for high-performance control multiphase drives due to their fast dynamic response, ability to handle multiple targets and constraints, and adaptability to different power converters or machine models. However, these techniques have some drawbacks, such as poor current reduction (x−y) and steady-state error (d−q), especially in the field weakening zone. Although some proposals have addressed these issues by adding modulation stages or designing new cost functions, there is still room for improvement, especially in steady-state error reduction. Therefore, this article proposes to include an integrator attached to a modulated predictive current controller applied to a six-phase induction machine to improve its performance throughout the entire speed range regarding steady-state error mitigation. Experimental tests were carried out to validate the effectiveness of the proposed controller. Tests were carried out evaluating the reduction of the steady-state error (d−q), the current tracking, the (x−y) currents reduction and the total harmonic distortion.

Power Electronics, Machines, and Control Electrification Workshop [Society News

Power Electronics, Machines, and Control Electrification Workshop [Society News

Minimum current stress control strategy for three degree of freedom three-phase dual active bridge DC-DC converter

Compared to single-phase dual active bridge (1p-DAB) DC-DC converters, three-phase dual active bridge (3p-DAB) DC-DC converters have advantages such as high single machine power, high power density, small filtering capacitance, and are more suitable for high-voltage situations. Therefore, they have good application prospects in DC transmission and industrial high-power DC-DC converters. However, under traditional single-phase shift (SPS) control, especially in the low power range, there is a large reactive current and severe soft switch loss. This article adopts an asymmetric modulation strategy for its larger reactive power, which reduces its reactive power in the low power range with more degrees of freedom and improves the efficiency of power transmission. Taking current stress as the optimization objective, the KKT algorithm is used to solve, and the corresponding analytical solution is ultimately obtained. Finally, a simulation is built by using MATLAB software to verify the feasibility of the proposed solution.

Influence of temperature on power factor and operating area of SynRM machine in automotive equipment

Across various applications, electrical machines are intensely replacing conventional hydraulic and pneumatic actuators in applications with a higher degree of complexity. In our previous study, a SynRM machine with a segmented rotor was designed to operate as a clutch actuator, to be placed in the gear housing which suffers from a high ambient temperature. This makes it necessary to predict the considerable potential influence of temperatures. This study evaluates the influence of winding resistance variation due to temperature on the machine power factor and its operating area. The evaluation is done for the condition of the automotive battery supply of 14 V, 50 A. An experimentally validated analytical model based on the SynRM machine phasor diagram was used to assess the torque-speed area and power factor variation. The main contribution is presented in the form of a tool represented as an abacus that allows the user of the machine to track the power factor and maximum speed for a range of winding resistance values. On a selected operating point of (Γ, N) = (0.57 N.m, 3500 rpm), it is demonstrated that the winding resistance should be reduced below 0.2 Ω, to be able to achieve the targeted speed, while the power factor is at 0.9.

Machine Learning Algorithm Comparison for the Performance Evaluation of Manual Welding Process

With the development of technology, the shipbuilding industry has seen a rise in automated welding processes. However, manual welding continues to be a necessary and in-demand skill. Unfortunately, the supply of both high-skilled and unskilled welders has steadily declined over the past decade, leading to a shortage of professional manpower. To address the issue of manpower shortage, a proposal has been made to provide timely and efficient training program for unskilled welders. However, evaluating the effectiveness of the training has proven challenging due to the lack of clear criteria for assessing the performance. This paper conducts an effective performance evaluation of unskilled welders using powerful machine learning algorithms. The evaluation is based on a dataset collected from both high-skilled and unskilled welder groups in manual welding processes. A comparison study is conducted to determine the most suitable algorithm. The goal is to identify the positive and negative parameters in the training of the manual welding process and provide an effective education strategy for unskilled welders. Additionally, the paper aims to find the algorithm with the highest accuracy. Overall, this study seeks to provide a solution to the shortage of manual welding professionals through the development of an efficient education strategy.

MODELING OF THE EXTERNAL MAGNETIC FIELD OF ELECTRIC MACHINES

Powerful electric machines – such as electric generators, electric motors generate a magnetic field of great tension. These fields negatively effect on personnel and can to violate the stability of electronic equipment. To determine safe areas for workers, laying communication cables and placing sensitive electronic equipment, it is advisable to model the propagation of magnetic fields of electrical machines. This will make it possible to rationalize the placing of electrical equipment at design stages. The most common high-power electrical machines are four-pole electrical machines with a dipole-quadrupole structure of the external magnetic field. The purpose of the research is a development of models of the propagation of the external magnetic field generated by alternating current electric machines. Results of the research: it is substantiated that to simulate the propagation of the magnetic field of electric machines, it is advisable to use the Gauss equation for the magnetic scalar potential. This will make it possible to take into account the required number of spatial harmonics of the magnetic field to ensure an acceptable calculation error. An electric machine is considered in a spherical approximation. Calculations were carried out in spherical coordinates. The distances were determined in relative radii of the electric machine - the ratio of the radius of the machine to the definition of field strength. The calculations were made for two planes of spherical coordinates and a three-dimensional image was obtained. As a result of the simulation, it is possible to determine the magnetic field strength of a four-pole electric machine at selected distances and directions around the electric machine with the required accuracy. It has been established that there are points of zero external magnetic field strength around electrical machines. Verification of the simulation results was carried out using the method of full-scale measurements of the magnetic field strength around a real four-pole machine. The measurement results showed acceptable agreement with the calculated data. Conclusions: the chosen approach and the results of modeling the propagation of the external magnetic field of electrical machines can be used to design the placement of electrical equipment, taking into account the requirements for electromagnetic safety and electromagnetic compatibility of technical equipment.

Using a simple radial basis function neural network to predict the glass transition temperature of alkali borate glasses

Artificial Neural Networks (ANN) are powerful machine learning algorithms. In the context of glass science, ANNs have been successfully used to induce composition-property regression models. These models are already influencing the way that we design new glasses, moving away from the traditional “cook and look” approach to computer-aided design. In this work, we induced an ANN model for the glass transition temperature Tg for glasses of the family xM2O⋅(100−x)B2O3, where M = Li, Na, K, Rb, and Cs, using simple radial basis function neural networks (RBF) with only two neurons. Statistically, the results of our methodologies are comparable to other complex models (empirical or physical) available in the literature with more neurons, such as the recent GlassNet and the topological model proposed by Mauro and co-authors (2009). This result supports the idea that a simpler specialized model can perform better than a complex general model for a restricted training domain.

Accelerating the identification of the allergenic potential of plant proteins using a stacked ensemble-learning framework

ABSTRACT: Plant-allergenic proteins (PAPs) have the potential to induce allergic reactions in certain individuals. While these proteins are generally innocuous for the majority of people, they can elicit an immune response in those with particular sensitivities. Thus, screening and prioritizing the allergenic potential of plant proteins is indispensable for the development of diagnostic tools, therapeutic interventions or medications to treat allergic reactions. However, investigating the allergenic potential of plant proteins based on experimental methods is costly and labour-intensive. Therefore, we develop StackPAP, a three-layer stacking ensemble framework for accurate large-scale identification of PAPs. In StackPAP, at the first layer, we conducted a comprehensive analysis of an extensive set of feature descriptors. Subsequently, we selected and fused five potential sequence-based feature descriptors, including amphiphilic pseudo-amino acid composition, dipeptide deviation from expected mean, amino acid composition, pseudo amino acid composition and dipeptide composition. Additionally, we applied an efficient genetic algorithm (GA-SAR) to determine informative feature sets. In the second layer, 12 powerful machine learning (ML) methods, in combination with all the informative feature sets, were employed to construct a pool of base classifiers. Finally, 13 potential base classifiers were selected using the GA-SAR method and combined to develop the final meta-classifier. Our experimental results revealed the promising prediction performance of StackPAP, with an accuracy, Matthew’s correlation coefficient and AUC of 0.984, 0.969 and 0.993, respectively, as judged by the independent test dataset. In conclusion, both cross-validation and independent test results indicated the superior performance of StackPAP compared with several ML-based classifiers. To accelerate the identification of the allergenicity of plant proteins, we developed a user-friendly web server for StackPAP (https://pmlabqsar.pythonanywhere.com/StackPAP). We anticipate that StackPAP will be an efficient and useful tool for rapidly screening PAPs from a vast number of plant proteins. Communicated by Ramaswamy H. Sarma

High School and Undergraduate Student Volunteers as an Imperfect Solution to Machine Learning Geoscience Research Needs

AbstractThe machine learning revolution presents geoscientists with exciting new opportunities for research, but is constrained by the need for large, high quality training data sets. Simultaneously, undergraduate and graduate program admissions have become increasingly competitive, pressuring high school and undergraduate students to differentiate themselves through involvement in research at earlier stages. Aligning these two interests provides mutually beneficial opportunities for both geoscientists and early‐stage students. We describe our experiences working with 20 early‐stage students to build a large training data set digitized from satellite images of meltwater drainage patterns on ice sheets. The intent of this Perspective is to share our experience and lessons learned with other machine learning researchers who, like us, may have minimal experience mentoring young volunteer researchers but may seek such partnerships for the first time in response to their machine learning training data set needs. These partnerships enabled creation of a powerful new machine learning model that would have otherwise been infeasible. Student benefits varied with their commitment and proactiveness, ranging from exposure to geoscience research and a resume line item to strong letters of recommendation and ongoing connections with geoscience researchers at an elite university lab. Many students were attracted to the project solely out of interest in machine learning, so the opportunity reached students who would not otherwise have conducted research in geoscience. Still, without incentives for researchers to engage less‐privileged students, our experience suggests that mutually beneficial partnerships between researchers and early‐stage students may exacerbate issues of inequality and lack of diversity within the geosciences.

Growing Restiveness of the Peasantry in Contemporary India: Context and Challenges

The global rise of neoliberalism has drastically altered the economic landscape of the peasantry and deepened the agrarian crisis of the countries of the Global South, including India. The roots of India’s agrarian crisis can be traced to a very significant transition from dirigiste to a neoliberal macroeconomic policy regime, in 1991, which has continued till date. Its most gruesome manifestation has been high and ever-rising farmers’ suicides. Factors such as substantial compression of rural development expenditures, increasing input prices, vulnerability to world market price fluctuations due to greater openness, inadequate crop insurance and substantial weakening of the provisioning for credit, along with the governments’ apathy to the demand for remunerative prices for farm produce, are among the obvious causal correlates of the contemporary agrarian crisis in the country. An important consequence has been a steady building up of peasant resistance, particularly over the last decade, leading up to the recent mass protests. Given their scale, intensity, and tenacity, they have been widely hailed as among the most significant resistance movements within the country and across the world against the machinations of corporate power and the interests of big business. This article addresses some of the primary features of the farmers’ movement in India, and the contradictions and challenges with which it has been contending.

Point projection radiography of electromagnetically accelerated flyer plates with an external X-pinch driver.

A platform for flyer plate benchmarking experiments has been developed, with an external X-pinch driver for point projection radiography. The experiments were performed using CEPAGE, a low inductance pulsed power machine at First Light Fusion (2 MA, 1.4 µs), with a new vacuum transmission line and flyer load hardware designed specifically to give a line of sight for radiography. A broadband 10-20keV x-ray source was produced by a portable X-pinch driver (140kA, 350ns) [Strucka etal., Matter Radiat. Extremes 7, 016901 (2021)] and was used to image the flyer. Radiography compliments the pre-existing diagnostic suite, which consists of current probes, velocimetry, and side-on optical probing of the impact shock transmitted into a transparent sample. The platform allows for significant insights into the 2D and 3D nature of the flyer launch, such as deformation and instability formation. It was used to diagnose a 10 × 9 × 1mm3 aluminum flyer, which reached a peak velocity of 4.2 km s-1 before impact with a poly(methylmethacrylate) sample. The experimental configuration, on-shot source characterization, and the results from two flyer plate experiments on CEPAGE are discussed.