Developed Modeling Technique Research Articles

Hyper‐parameter optimized GPR model based on chaos game algorithm for RF power transistors

AbstractIn this paper, a new frequency domain behavior model for radio frequency (RF) power transistors based on a hyper‐parameter optimized Gaussian process regression (GPR) method is presented. The chaos game optimization (CGO) algorithm is used to optimize GPR hyperparameters, resulting in the CGO‐GPR model. The basic theory as well as the details of the modeling process are presented. Validation of the model is conducted using a 10‐watt GaN power transistor. Compared to the standard GPR model, the proposed model achieved a significant improvement. Furthermore, the comparison with the particle swarm optimization (PSO) based GPR model (PSO‐GPR) showed that the proposed model allows achieving superior performance, thereby confirming the effectiveness of the developed modeling technique.

Grid-Characteristic Method for Calculation of Discontinuous Non-Steady Flows of a Multicomponent Reacting Gas in Channels

This paper is devoted to the description of computational algorithms for modeling quasi-one-dimensional non-steady flows of a multicomponent reacting gas. The particularity of the developed modeling technique is that the paths of strong and weak discontinuities are mobile computational nodes, and the parameters for them are calculated using special algorithms. A set of programs has been developed, which can be used to solve the problems of the reacting gas dynamics that are of applied importance, as well as serve as an illustrator for physical gas dynamics training courses. The paper provides the results of the numerical modeling of the supersonic flow in a flat channel simulating the operation of experimental facilities of the Institute for Problems in Mechanics and the Institute of Physics and Technology. A satisfactory correlation between the calculated and experimental data has been obtained.

Mechanical modeling, seismic fragility, and correlation issues for groups of spherical pressure vessels

A roadmap is outlined for determining comprehensive seismic fragility curves for (single or groups of) spherical pressure vessel structures commonly found in oil refineries. The developed modeling techniques aim to strike a balance between accuracy and computational efficiency, with a focus on capturing the most pertinent failure modes relevant to these structural types. First, a set of “partial” fragilities is determined based on each vessel’s fill ratio, as the response varies substantially depending on the amount of liquid content. Considering that a seismic assessment process invariably involves simultaneous consideration of such partial fragilities, a Monte Carlo-based approach is employed for their combination. The results naturally depend on the level of correlation employed, but can be almost perfectly matched by simpler analytical methods in the edge cases of full and zero correlation.

Threshold Optimized CSWPL Behavioral Model for RF Power Transistors Based on Particle Swarm Algorithm

In this letter, the particle swarm optimization (PSO) is employed to optimize the threshold values of the canonical section-wise piecewise linear (CSWPL) function-based behavioral model of power transistors. The effectiveness of the proposed method is validated through measurements carried out on a 10-W GaN power transistor produced by Wolfspeed. Compared with the existing simultaneous perturbation stochastic approximation (SPSA) method, the developed modeling technique not only provides superior prediction performance across different input power levels but also finds the optimal thresholds much more efficiently.

Modeling and assessment of the energy state of the technological system of mechanical processing when creating digital twins

An approach to the construction of digital twins of the technological system for turning low rigidity parts and the assessment of the energy state of the technological system is proposed in this article. The creating of the digital twin models by differential equations allows to excide a time-consuming procedure for training neural networks. The results obtained are transmitted to the energy state assessment block. Calculations are performed to determine the power consumption between the moving parts of the machine and the cutting process. To determine the energy, we use the Hamilton equations. The developed modeling technique and the results of computational experiments will provide an operational and resource-saving mode of production in the machining process.

The use of machine learning tools for modeling the countermeasure environment of robotic means and mobile objects of monitoring

In this article, an analysis of research related to the problems and areas of application of machine learning was carried out and it becomes clear that reinforcement learning is an important tool for the development of highly effective and adaptive control systems. This approach opens perspectives for the development of intelligent systems that can effectively adapt to changes in the environment and provide a reliable and optimal level of control under conditions of uncertainty and variability. In the course of the research, a complex environment modelling technique was developed for the task of searching and chasing moving objects by robotic means as part of reinforcement learning. The methodology includes defining goals and objectives, modelling the environment, defining states, actions, and rewards, formulating the state transition function, defining the reward function, modelling completion criteria, using convolutional neural networks to analyse the environment, and integrating the model into reinforcement learning algorithms. A feature of the developed methodology is its ability to adapt to various environmental conditions and dynamic changes occurring in it. The use of graphical representation of the environment allows you to reproduce in detail the real conditions in which the robotic means operate, including obstacles, areas of visibility and different types of surfaces. The use of convolutional neural networks for environmental analysis is an innovative approach that allows you to automate the process of determining the impact of the environment on the parameters of robotic vehicles and moving objects. CNN training on the collected data about the environment provides accurate prediction of influence coefficients in different areas, which allows optimizing strategies of robot behaviour depending on changes in conditions. In general, the developed environment modelling technique allows not only to accurately reproduce the real conditions in which robotic means operate, but also provides flexibility and adaptability when environmental conditions change. This opens up vast opportunities for training and improving reinforcement learning algorithms, increasing the effectiveness of robots in performing their tasks in various real-world scenarios.

Stacking- and voting-based ensemble deep learning models (SEDL and VEDL) and active learning (AL) for mapping land subsidence.

This contribution presents a novel methodology based on the feature selection, ensemble deep learning (EDL) models, and active learning (AL) approach for prediction of land subsidence (LS) hazard and rate, and its uncertainty in an area involving two important plains - the Minab and Shamil-Nian plains - in the Hormozgan province, southern Iran. The important features controlling LS hazard were identified by ridge regression. Then, two EDL models were constructed by stacking (SEDL) and voting (VEDL) five dense deep learning (DL) models (model 1 to model 5) for mapping LS hazard. Thereafter, the predictive model performance was assessed by a precision-recall curve and Kolmogorov-Smirnov (KS) plot. A partial dependence plot (PDP), individual conditional expectation plots (ICEP), game theory, and a sensitivity analysis were used for the interpretability of the predictive DL model. According to SEDL - a model with higher accuracy - 34% (1624 km2), 14.7% (698 km2), and 19.2% (912 km2) of the total area were classified as being of very low, low, and moderate hazards, whereas 17.7% (845 km2) and 14.4% (683 km2) of area were classified as being of high and very high hazards, respectively. Based on all interpretability techniques, aquifer loss or groundwater drawdown is the most important feature controlling LS hazard, and it having the greatest impact on the SEDL model output. Based on a Taylor diagram and R2 as model performance assessment indicators, SEDL-AL (with R2 > 95% for training and test datasets) performed better than SEDL for quantify LS rate, the rate of LS ranging between 0 and 48.1cm. The highest rate of LS occurred in the Minab plain - an area located downstream of the Minab Esteghlal dam. SEDL-AL was used to quantify the uncertainty associated with the LS rate. The observed values fell within predictions provided by SEDL-AL, which indicates a high accuracy of our predictive model. Overall, our newly developed modeling techniques are helpful tools for the spatial mapping of LS susceptibility and rate, and its uncertainty.

Accurate Efficiency and Power Densities Optimization of Output Inductor of Buck Derived Converters

In this article, inductor loss models are developed based on the experimental characterization of off-the-shelf components. The modelling steps and techniques are described and validated. It is shown that the model exhibits fairly good accuracy over a large range of ripple current frequency and magnitude. Then, these models are used, as an illustration, in order to present the possible optimization process of the tradeoff between switching frequency-current ripple magnitude and output inductors value in the case of a Buck-derived converter. This optimization has shown that a large current ripple may lead to minimized losses in some cases. The developed modelling technique aims to represent Joules and iron losses, as well as DC and AC losses of inductors. It is not based on physical behaviour description but on mathematical equations based on a set of experimental characterizations. The modelling technique is not suitable for designing the component itself but is useful for selecting the best component value in the manufacturer’s series of components. Since it remains difficult with the manufacturer datasheet to estimate AC losses accurately with respect to frequency and ripple current magnitude, a specific characterization is carried out to complement the available data.

Seismic protection by rocking with superelastic tendon restraint

AbstractThis article introduces an innovative system for enhancing the seismic performance of a structure through facilitating large rotational (rocking) motion to occur without risking overturning. The innovation of this study is in the use of tendons consisting of Nickel‐Titanium (superelastic) alloy connected in series with steel to impose partial restraints to the structure when experiencing rocking motion. Importantly, the large rotational motion is fully recoverable. Existing installations which can be made to rock may also be retrofitted with the device for improving its seismic resistance. The original contributions of the article are the derivation, and experimental validation, of an analytical model for simulating the seismic performance of a system that has been fitted with the restraining device. In a parametric study employing the newly developed modelling techniques, major trends in the seismic response behaviour of the structure have been identified.

Deep Learning Models to Determine Nutrient Concentration in Hydroponically Grown Lettuce Cultivars (Lactuca sativa L.)

Deep learning (DL) and computer vision applications in precision agriculture have great potential to identify and classify plant and vegetation species. This study presents the applicability of DL modeling with computer vision techniques to analyze the nutrient levels of hydroponically grown four lettuce cultivars (Lactuca sativa L.), namely Black Seed, Flandria, Rex, and Tacitus. Four different nutrient concentrations (0, 50, 200, 300 ppm nitrogen solutions) were prepared and utilized to grow these lettuce cultivars in the greenhouse. RGB images of lettuce leaves were captured. The results showed that the developed DL’s visual geometry group 16 (VGG16) and VGG19 architectures identified the nutrient levels of lettuces with 87.5 to 100% accuracy for four lettuce cultivars, respectively. Convolution neural network models were also implemented to identify the nutrient levels of the studied lettuces for comparison purposes. The developed modeling techniques can be applied not only to collect real-time nutrient data from other lettuce type cultivars grown in greenhouses but also in fields. Moreover, these modeling approaches can be applied for remote sensing purposes to various lettuce crops. To the best knowledge of the authors, this is a novel study applying the DL technique to determine the nutrient concentrations in lettuce cultivars.

Benefits of Cyber-Physical Systems Modeling and Simulation with LabView

Cyber-physical systems (CPSs) as part of the Industry 4.0 strategy, represents one of the most challenging research topic for engineers. It’s well known that CPSs integrate at highest level digital technology (computation, control and networking) into physical objects. However, by incorporating various heterogeneous subsystems with different energy levels and functionalities, both analogue and digital signals management, as well as a large scale of communication and information technologies, their modeling and simulation becomes a difficult engineering task. In the past years a huge number of research papers has been dedicated to identify and develop modeling techniques and simulation toolkits being able to handle CPSs complexity. Following these trends, this paper is focused to research and evidence issues linked with the LabView graphically oriented programming technology utilization for CPSs modelling and simulation purposes. Both advantages and shortcomings of this very special technology are studied in order to design and implement a viable software framework being able to model and simulate various CPS structures. As a concrete example, a specific CPS configuration consist of six computer-based mechatronic systems that constitute a laboratory-prototype manufacturing plant has been chosen for LabView-based modeling and simulation. Various virtual instrument-type models of this setup has been conceived and proposed for real-time simulation. It has been concluded then that the application of LabView technology lead to interesting and useful results. The paper specially highlights the benefits and versatility of LabView utilization for complex CPSs modeling and simulation purposes.

Finite element modelling of reinforced masonry walls under axial compression

This paper presents the development of 3D finite element (FE) technique to model and analyse reinforced masonry (RM) walls under axial compression. The Arc-length algorithm integrated with initial geometric imperfection has been used to model the geometric nonlinear response of both the embedded steel and that of the RM wall to allow for the occurrence of buckling under concentric compression. A segmental modelling technique was developed to consider geometric and material nonlinearities of each component of a RM wall such as block, mortar, grout and reinforcement bars. The modelling parameters were calibrated using the RM wall experimental testing program previously conducted by the authors in which three series of RM walls with different slenderness ratios (4, 7 and 12) were tested under axial compression. The applicability of the models was verified using the experimental data in terms of axial load-deflection responses and strain in vertical steel bars. It was determined that the developed modelling technique was able to capture the experimental responses with reasonable accuracy. Further, the verified FE model was used to predict the responses of RM walls of higher slenderness ratios (21, 26, 32 and 42) to examine the probable buckling of taller RM walls. The failure modes and the ultimate capacity of slender RM walls have been reported and the potential of using the RM for taller walls are discussed against the existing code provisions.

Dynamic relationships among phosphate rock, fertilisers and agricultural commodity markets: Evidence from a vector error correction model and Directed Acyclic Graphs

The finite supply of phosphate rock, as well as rising fertiliser prices, are key topics in the discussion around global food system resilience. Our paper contributes to this discussion by conducting an analysis of the dynamic causal relationships between phosphate rock, fertilisers, and wheat prices to provide insights on how farmers and policymakers might respond to phosphate rock supply shocks for sustainable and resilient food systems. The linkages between 147 monthly price observations spanning from March 2007 to April 2019 were analysed by combining Directed Acyclic Graphs (DAG), a recently developed modelling technique, and a Vector Error Correction Model (VECM). The findings suggest that there are five long-run cointegrating relationships between these three key components of the food supply chain. Price shocks to the phosphate rock market, over a two-year period had a knock-on positive impact on phosphorus fertiliser prices and to a lesser extent on wheat prices. Interestingly, an increase in wheat price had a sizeable impact on both fertiliser and phosphate rock prices, providing empirical evidence that increases in the price of phosphate rock are driven by demand factors, as well as supply factors.

Detection of false data cyber-attacks for the assessment of security in smart grid using deep learning

Smart Grid uses electricity and information flows to set up a highly developed, fully automated, and distributed electricity grid system. To identify the reliability of work and availability, cyber attacks detection in the smart grids play a significant role. This paper highlights the integrity of false data cyber-attacks in the physical layers of smart grids. As the first contribution, the Proposed True Data Integrity provides an attack exposure metric through an Agent-Based Model. Next, the research focuses on the decentralization of Data Integrity Security in the system with an Agent-based approach. Finally, the productivity and efficiency of the developed modeling techniques are experimentally evaluated and compared with the existing state-of-the-art supervised deep-learning models. The obtained results of the studies have shown the improved false data detection accuracy of 98.19% through replay cyber-attacks using the Artificial Feed-forward Network. Based on the research findings, deep neural network can be used to assess cyber data in smart grids to detect malware incidents and attacks.

Mathematical Models for a Social Partitioning Problem

In this paper we develop modeling techniques for a social partitioning problem. Different social interaction regulations are imposed during pandemics to prevent the spread of diseases. We suggest partitioning a set of company employees as an effective way to curb the spread, and use integer programming techniques to model it. The goal of the model is to maximize the number of direct interactions between employees who are essential for company’s work subject to the constraint that all employees should be partitioned into components of no more than a certain size implied by the regulations. Then we further develop the basic model to take into account different restrictions and provisions. We also give heuristics for solving the problem. Our computational results include sensitivity analysis on some of the models and analysis of the heuristic performance.

Large-Signal Modeling of GaN HEMTs Using Hybrid GA-ANN, PSO-SVR, and GPR-Based Approaches

This article presents an extensive study and demonstration of efficient electrothermal large-signal GaN HEMT modeling approaches based on combined techniques of Genetic Algorithm (GA) with Artificial Neural Networks (ANN), and Particle Swarm optimization (PSO) with Support Vector Regression (SVR). Another promising Gaussian Process Regression (GPR) based large-signal modeling approach is also explored and presented. The GA-ANN addresses the typical problem of local minima associated with the backpropagation (BP) based ANN. The GA successfully aids in the determination of optimal initial values for BP-ANN and enables it to find a unique optimal solution after subsequent of iterations with higher rate of convergence. This is also achieved using PSO-SVR with lower optimization variables. The developed modeling techniques are demonstrated and used to simulate the gate and drain currents of a 2-mm GaN device. All the models are relatively simple, practical, and easy to implement. The gate and drain currents models are embedded in an equivalent large-signal circuit's model and built in Advanced Design System (ADS) software. The implemented model is validated by large-signal measurements and very good fitting results have been obtained. The model also showed an accurate simulation for a nonlinear power amplifier with very good computational speed and convergence.

Modelling and Simulation of a Fishing Rod (Flexible Link) Using Simmechanics

In this work, the modeling of a single-link flexible manipulator has been done using simmechanics tool of Matlab and treated as a fishing rod. An elastic string is attached to the free end of the rod. A payload is given to the open end of the string for the deflection analysis of the flexible rod. The simmechanics model of the flexible rod has been developed using the lumped parameter approach. Initially, the developed modeling technique has been validated by comparing the deflection obtained from the proposed model simulation and the conventional formulae with particular payload at the free end. Later on, to attain the fishing rod-like structure, the cross-section of the rod has been made taper towards its open end. Then, different loading conditions have been applied to the free end of the string, and the model behavior has been studied. Results obtained from the simulated model are presented and discussed under all the loading conditions.

Recent advances on industrial data-driven energy savings: Digital twins and infrastructures

Data-driven models for industrial energy savings heavily rely on sensor data, experimentation data and knowledge-based data. This work reveals that too much research attention was invested in making data-driven models, as supposed to ensuring the quality of industrial data. Furthermore, the true challenge within the Industry 4.0 is with data communication and infrastructure problems, not so significantly on developing modelling techniques. Current methods and data infrastructures for industrial energy savings were comprehensively reviewed to showcase the potential for a more accurate and effective digital twin-based infrastructure for the industry. With a few more development in enabling technologies such as 5G developments, Internet of Things (IoT) standardization, Artificial Intelligence (AI) and blockchain 3.0 utilization, it is but a matter of time that the industry will transition towards the digital twin-based approach. Global government efforts and policies are already inclining towards leveraging better industrial energy efficiencies and energy savings. This provides a promising future for the development of a digital twin-based energy-saving system in the industry. Foreseeing some potential challenges, this paper also discusses the importance of symbiosis between researchers and industrialists to transition from traditional industry towards a digital twin-based energy-saving industry. The novelty of this work is the current context of industrial energy savings was extended towards cutting-edge technologies for Industry 4.0. Furthermore, this work proposes to standardize and modularize industrial data infrastructure for smart energy savings. This work also serves as a concise guideline for researchers and industrialists who are looking to implement advanced energy-saving systems.

Computer models of gas-dynamic processes of radionuclides behavior in thermal emission converter of nuclear power plant

The paper is devoted to the application of numerical solution of the Boltzmann equation method for modeling the behavior of radionuclides (Xe and Kr) in the inter-electrode gap and the vacuum-cesium channel of a thermionic reactor-converter, which is used in a space nuclear power generator. In this work, we developed modeling techniques and implemented them in a software package, that is using the algorithm of simultaneous calculations for the left side of the Boltzmann equation. We performed series of calculations for different initial flux of radionuclides and evaluated the dependence of the radionulcides output flux on the input flux for two areas of the reactor.

The method for determining the profile of large diameter pipes and the optimal technological mode during calibration-bending in the weld zone

The article presents the results of finite-element modeling of the local calibration-bending process of large-diameter pipes in the weld zone with control of the dynamics changes in the geometry of the inner and outer surfaces of the workpiece, the base diameter, the total deformation of the perimeter and ovalization of the contours. The author has developed the technique of determining the coordinates of surface grid nodes based on an algorithm implemented in a special LUA-program for the QForm complex. The developed modeling technique allows us to determine the optimal working stroke of the tool and other parameters of the local calibration of the tube billet to minimize its degree of ovalization. An example of the implementation of the local calibration method and the predicted change in the geometry of the contour of the pipe billet with diameter φ1420×40 made of K60 steel with the initial shape defects after welding is given. The technical implementation of the method of local correction and prediction of the tube billet profile is complemented by the possibility of editing it by expansion. Improving the accuracy of geometry in the end zones of pipes will directly increase the possibility of high quality butt-welding during installation of pipeline systems.