Search results for: hyperparameter tuning

Authors: R. Dakir, J. Zbitou, Ahmed Mouhsen, A. Errkik, A. Tajmouati, M. Latrach

Abstract:

The design and analysis of a new compact and miniaturized monopole antenna structure for ultra wideband (UWB) wireless applications are presented and suggested in this paper. The proposed antenna structure is based on corner radiator patch with T-shaped slot and fed by mictostrip feed line with a partial ground plane combined a periodic rectangular slot and inverted T-stub tuning to increase the bandwidth. The design parameters and the performance of the suggested antenna are investigated by using 'CST Microwave Studio' and Advanced Design System. The final prototype of the proposed antenna operates from 3GHZ to 25GHz, corresponding to wide input impedance bandwidth around (157.14%) with a size of 16*24mm2 and can be easily integrated with radio-frequency or microwave circuits with low cost manufacturing. Details of the UWB antenna design and both simulated and measured results are described and discussed.

Keywords: UWB, T-shaped slots, improvement, bandwidth, stub tuning

Procedia PDF Downloads 294

Authors: M. Ananthakrishnan, Sunil K Patil, Koti Naveen, Inuganti Hemanth Kumar

Abstract:

State estimation output of EMS forms the base case for all other advanced applications used in real time by a power system operator. Ensuring tuning of state estimator is a repeated process and cannot be left once a good solution is obtained. This paper attempts to demonstrate methods to improve state estimator solution by identifying incorrect modelling and telemetry inputs to the application. In this work, identification of database topology modelling error by plotting static network using node-to-node connection details is demonstrated with examples. Analytical methods to identify wrong transmission parameters, incorrect limits and mistakes in pseudo load and generator modelling are explained with various cases observed. Further, methods used for active and reactive power tuning using bus summation display, reactive power absorption summary, and transformer tap correction are also described. In a large power system, verifying all network static data and modelling parameter on regular basis is difficult .The proposed tuning methods can be easily used by operators to quickly identify errors to obtain the best possible state estimation performance. This, in turn, can lead to improved decision-support capabilities, ultimately enhancing the safety and reliability of the power grid.

Keywords: active power tuning, database modelling, reactive power, state estimator

Procedia PDF Downloads 7

Authors: Hossein Alimohammadi, Kristina Vassiljeva, Hassan HosseinNia, Eduard Petlenkov

Abstract:

This research article discusses the mechanisms for bandgap tuning of beam-type resonators to achieve ‎broadband vibration suppression through adjustable stiffness. The method involves changing the center of ‎mass of the cantilever-type resonator to achieve piezo-free tuning of stiffness. The study investigates the ‎effect of the center of masses variation (δ) of attached masses on the bandgap and vibration suppression ‎performance of a non-uniform beam-type resonator within a phononic structure. The results suggest that the ‎cantilever-type resonator beam can be used to achieve tunability and real-time control and indicate that ‎varying δ significantly impacts the bandgap and transmittance response. Additionally, the research explores ‎the use of the first and second modes of resonators for tunability and real-time control. These findings examine ‎the feasibility of this approach, demonstrate the potential for improving resonator performance, and provide ‎insights into the design and optimization of metamaterial beams for vibration suppression applications.

Keywords: bandgap, adjustable stiffness, spatial variation, tunability

Procedia PDF Downloads 85

Authors: Kaddari Faiza, Mazari Benyounes, Mihoub Youcef, Safa Ahmed

Abstract:

Active filtering of electric power has now become a mature technology for reactive power and harmonic compensation caused by the proliferation of power electronics devices used for industrial, commercial and residential purposes. The aim of this study is to enhance the power quality by improving the performances of shunt active power filter in harmonic mitigation to obtain sinusoidal source currents with very weak ripples. A power circuit configuration and control scheme for shunt active power filter are described with an improved method for harmonics compensation using self-tuning-filter for harmonics identification and fuzzy logic control to generate reference current. Simulation results (using MATLAB/SIMULINK) illustrates the compensation characteristics of the proposed control strategy. Analysis of these results proves the feasibility and effectiveness of this method to improve the power quality and also show the performances of fuzzy logic control which provides flexibility, high precision and fast response. The total harmonic distortion (THD %) for the simulations found to be within the recommended imposed IEEE 519-1992 harmonic standard.

Keywords: Active Powers Filter (APF), Self-Tuning-Filter (STF), fuzzy logic control, hysteresis-band control

Procedia PDF Downloads 737

Authors: Jin-Sup Kim, Se-Hwan Choi, Jae-Young Lee

Abstract:

A 8-bit CMOS capacitor array is designed for using in electrically steerable passive array radiator (ESPAR). The proposed capacitor array shows the fast response time in rising and falling characteristics. Compared to other works in silicon-on-insulator (SOI) or silicon-on-sapphire (SOS) technologies, it shows a comparable tuning range and switching time with low power consumption. Using the 0.18um CMOS, the capacitor array features a tuning range of 1.5 to 12.9 pF at 2.4GHz. Including the 2X4 decoder for control interface, the Chip size is 350um X 145um. Current consumption is about 80 nA at 1.8 V operation.

Keywords: CMOS capacitor array, ESPAR, SOI, SOS, switching time

Procedia PDF Downloads 589

Authors: Muhammad Haitham Albahnassi, Adnan Malki, Shokri Almekdad

Abstract:

In this paper, a method for reconfiguring bandwidth in a circular dual-mode resonator is presented. The method concerns the optimized geometry of a structure that may be used to host the tuning elements, which are typically RF (Radio Frequency) switches. The tuning elements themselves, and their performance during tuning, are not the focus of this paper. The designed resonator is able to reconfigure its fractional bandwidth by adjusting the inter-coupling level between the degenerate modes, while at the same time improving its response by adjusting the external-coupling level and keeping the center frequency fixed. The inter-coupling level has been adjusted by changing the dimensions of the perturbation element, while the external-coupling level has been adjusted by changing one of the feeder dimensions. The design was arrived at via optimization. Agreeing simulation and measurement results of the designed and implemented filters showed good improvements in return loss values and the stability of the center frequency.

Keywords: dual-mode resonators, perturbation theory, reconfigurable filters, software defined radio, cognitine radio

Procedia PDF Downloads 167

Authors: Kiamran Radjabli

Abstract:

State Estimator became an intrinsic part of Energy Management Systems (EMS). The SCADA measurements received from the field are processed by the State Estimator in order to accurately determine the actual operating state of the power systems and provide that information to other real-time network applications. All EMS vendors offer a State Estimator functionality in their baseline products. However, setting up and ensuring that State Estimator consistently produces a reliable solution often consumes a substantial engineering effort. This paper provides generic recommendations and describes a simple practical approach to efficient tuning of State Estimator, based on the working experience with major EMS software platforms and consulting projects in many electrical utilities of the USA.

Keywords: convergence, monitoring, state estimator, performance, troubleshooting, tuning, power systems

Procedia PDF Downloads 156

Authors: Savita, Pargam Vashishtha, Govind Gupta, Ankush Vij, Anup Thakur

Abstract:

The ligand field dependent visible as well as NIR emission of the Cr³+dopant in spinel hosts has attracted immense attention in tuning the color emitted by the material. In this research, Mg1-xCrxAl₂O₄(x=0.5, 1, 3, 5, and 10 mol%) nanocrystals have been synthesizedby solution combustion method. The synthesized nanocrystals possessed a single phase cubic structure. The strong absorption by host lattice defects (antisite defects, F centres) andd-d transitions of Cr³+ ions lead to radiative emission in the visible and NIR region, respectively. The red-NIR emission in photoluminescence spectra inferred the octahedral symmetry of Cr³+ ions and anticipated the site distortion by the presence ofCr³+ clusters and antisite defects in the vicinity of Cr³+ ions. The thermoluminescence response of UV and γ-irradiated Cr doped MgAl2O4 samples revealed the formation of various shallow and deep defects with doping Cr³+ions. The induced structural cation disorder with an increase in doping concentration caused photoluminescence quenching beyond 3 mol% Cr³+ doping. The color tuning exhibited by Cr doped MgAl₂O₄ nanocrystals by varying Cr³+ ion concentration and excitation wavelength find its applicability in solid state lighting.

Keywords: antisite defects, cation disorder, color tuning, combustion synthesis

Procedia PDF Downloads 178

Authors: Alirıza Kaleli, M. Akif Ceviz, Erdoğan Güner, Köksal Erentürk

Abstract:

The cyclic variations in spark ignition engines occurring especially under specific engine operating conditions make the maximum pressure variable for successive in-cylinder pressure cycles. Minimization of cyclic variations has a great importance in effectively operating near to lean limit, or at low speed and load. The cyclic variations may reduce the power output of the engine, lead to operational instabilities, and result in undesirable engine vibrations and noise. In this study, spark timing is controlled in order to reduce the cyclic variations in spark ignition engines. Firstly, an ARMAX model has developed between spark timing and maximum pressure using system identification techniques. By using this model, the maximum pressure of the next cycle has been predicted. Then, self-tuning minimum variance controller has been designed to change the spark timing for consecutive cycles of the first cylinder of test engine to regulate the in-cylinder maximum pressure. The performance of the proposed controller is illustrated in real time and experimental results show that the controller has a reliable effect on cycle to cycle variations of maximum cylinder pressure when the engine works under low speed conditions.

Keywords: cyclic variations, cylinder pressure, SI engines, self tuning controller

Procedia PDF Downloads 481

Authors: Santosh Kumar Suman, Vinod Kumar Giri

Abstract:

The goal of this paper is to outline a speed controller of a DC motor by choice of a PID parameters utilizing genetic algorithms (GAs), the DC motor is extensively utilized as a part of numerous applications such as steel plants, electric trains, cranes and a great deal more. DC motor could be represented by a nonlinear model when nonlinearities such as attractive dissemination are considered. To provide effective control, nonlinearities and uncertainties in the model must be taken into account in the control design. The DC motor is considered as third order system. Objective of this paper three type of tuning techniques for PID parameter. In this paper, an independently energized DC motor utilizing MATLAB displaying, has been outlined whose velocity might be examined utilizing the Proportional, Integral, Derivative (KP, KI , KD) addition of the PID controller. Since, established controllers PID are neglecting to control the drive when weight parameters be likewise changed. The principle point of this paper is to dissect the execution of optimization techniques viz. The Genetic Algorithm (GA) for improve PID controllers parameters for velocity control of DC motor and list their points of interest over the traditional tuning strategies. The outcomes got from GA calculations were contrasted and that got from traditional technique. It was found that the optimization techniques beat customary tuning practices of ordinary PID controllers.

Keywords: DC motor, PID controller, optimization techniques, genetic algorithm (GA), objective function, IAE

Procedia PDF Downloads 419

Authors: Andrés Gomez-Casseres, Rubén Contreras

Abstract:

In this paper, a bidirectional boost converter operated in Discontinuous Conduction Mode (DCM) is presented as a suitable power conditioning circuit for tuning of kinetic energy harvesters without the need of a battery. A nonlinear control scheme, composed by two linear controllers, is used to control the average value of the input current, enabling the synthesization of complex loads. The converter, along with the control system, is validated through SPICE simulations using the LTspice tool. The converter model and the controller transfer functions are derived. From the simulation results, it was found that the input current distortion increases with the introduced phase shift and that, such distortion, is almost entirely present at the zero-crossing point of the input voltage.

Keywords: average current control, boost converter, electrical tuning, energy harvesting

Procedia PDF Downloads 762

Authors: J. Ritonja

Abstract:

Available commercial applications of power system stabilizers assure optimal damping of synchronous generator’s oscillations only in a small part of operating range. Parameters of the power system stabilizer are usually tuned for the selected operating point. Extensive variations of the synchronous generator’s operation result in changed dynamic characteristics. This is the reason that the power system stabilizer tuned for the nominal operating point does not satisfy preferred damping in the overall operation area. The small-signal stability and the transient stability of the synchronous generators have represented an attractive problem for testing different concepts of the modern control theory. Of all the methods, the adaptive control has proved to be the most suitable for the design of the power system stabilizers. The adaptive control has been used in order to assure the optimal damping through the entire synchronous generator’s operating range. The use of the adaptive control is possible because the loading variations and consequently the variations of the synchronous generator’s dynamic characteristics are, in most cases, essentially slower than the adaptation mechanism. The paper shows the development and the application of the self-tuning power system stabilizer based on recursive least square identification method and linear quadratic regulator. Identification method is used to calculate the parameters of the Heffron-Phillips model of the synchronous generator. On the basis of the calculated parameters of the synchronous generator’s mathematical model, the synthesis of the linear quadratic regulator is carried-out. The identification and the synthesis are implemented on-line. In this way, the self-tuning power system stabilizer adapts to the different operating conditions. A purpose of this paper is to contribute to development of the more effective power system stabilizers, which would replace currently used linear stabilizers. The presented self-tuning power system stabilizer makes the tuning of the controller parameters easier and assures damping improvement in the complete operating range. The results of simulations and experiments show essential improvement of the synchronous generator’s damping and power system stability.

Keywords: adaptive control, linear quadratic regulator, power system stabilizer, recursive least square identification

Procedia PDF Downloads 247

Authors: Fatemeh Behbahani, Rubiyah Yusof

Abstract:

To avoid collision between following vehicles and vehicles in front, it is vital to keep appropriate, safe spacing between both vehicles over all speeds. Therefore, the following vehicle needs to have exact information regarding the speed and spacing between vehicles. This project is conducted to simulate the tuning of controller gain for a vehicle-following system through the selected control strategy, spacing control policy and fixed-time headway policy. In addition, the paper simulates and designs an adaptive gain controller for a road-vehicle-following system which uses information on the spacing, velocity and also acceleration of a preceding vehicle in the proposed one-vehicle look-ahead strategy. The mathematical model is implemented using Kirchhoff and Newton’s Laws, and stability simulated. The trial-error method was used to obtain a suitable value of controller gain. However, the adaptive-based controller system was able to optimize the gain value automatically. Model Reference Adaptive Control (MRAC) is designed and utilized and based on firstly the Gradient and secondly the Lyapunov approach. The Lyapunov approach considers stability. The Gradient approach was found to improve the best value of gain in the controller system with fixed-time headway.

Keywords: one-vehicle look-ahead, model reference adaptive, stability, tuning gain controller, MRAC

Procedia PDF Downloads 238

Authors: Un-Hwan Park, Jun-Hyeok Heo, In-Sung Lee, Tae-Hyeon Oh, Dae-Gyu Park

Abstract:

Nonwoven fabric such as an automobile interior material becomes consists of several material layers required for the sound-absorbing function. Because several material layers, many experimental tuning is required to achieve the target of sound absorption. Therefore, a lot of time and money is spent in the development of the car interior materials. In this study, we present the method to predict the sound-absorbing performance of the various layers with physical properties of each material. and we will verify it with the measured value of a prototype. If the sound absorption can be estimated, it can be optimized without a number of tuning tests of the interiors. So, it can reduce the development cost and time during development

Keywords: automotive interior material, sound absorbing, optimization design, nonwoven fabric

Procedia PDF Downloads 836

Authors: Amil Daraz, Suheel Abdullah Malik, Tahir Saleem, Sajid Ali Bhati

Abstract:

In this paper, Integral Proportional (I-P) controller is employed for superheated steam temperature control system. The Ziegler-Nichols (Z-N) method is used for the tuning of I-P controller. The performance analysis of Z-N based I-P controller is assessed on superheated steam system of 500-MW boiler. The comparison of transient response parameters such as rise time, settling time, and overshoot is made with Z-N based Proportional Integral (PI) controller. It is observed from the results that Z-N based I-P controller completely eliminates the overshoot in the output response.

Keywords: superheated steam, process reaction curve, PI and I-P controller, Ziegler-Nichols Tuning

Procedia PDF Downloads 331

Authors: Jose D. Herrera, Mario A. Rios

Abstract:

This paper deals with the coordinated tuning of the Power System Stabilizer (PSS) controller and Power Oscillation Damping (POD) Controller of Flexible AC Transmission System (FACTS) in a multi-machine power systems. The coordinated tuning is based on the critical eigenvalues of the power system and a model reduction technique where the Hankel Singular Value method is applied. Through the linearized system model and the parameter-constrained nonlinear optimization algorithm, it can compute the parameters of both controllers. Moreover, the parameters are optimized simultaneously obtaining the gains of both controllers. Then, the nonlinear simulation to observe the time response of the controller is performed.

Keywords: electromechanical oscillations, power system stabilizers, power oscillation damping, hankel singular values

Procedia PDF Downloads 592

Authors: Delowar Hossain, Genci Capi

Abstract:

This paper concerns with the problem of deep learning parameters tuning using a genetic algorithm (GA) in order to improve the performance of deep learning (DL) method. We present a GA based DL method for robot object recognition and grasping. GA is used to optimize the DL parameters in learning procedure in term of the fitness function that is good enough. After finishing the evolution process, we receive the optimal number of DL parameters. To evaluate the performance of our method, we consider the object recognition and robot grasping tasks. Experimental results show that our method is efficient for robot object recognition and grasping.

Keywords: deep learning, genetic algorithm, object recognition, robot grasping

Procedia PDF Downloads 353

Authors: Hesham Abdin, Mohamed Zakaria, Talaat Abd-Elmonaem, Alaa El-Din Sayed Hafez

Abstract:

Kalman filter algorithm is an estimator known as the workhorse of estimation. It has an important application in missile guidance, especially in lack of accurate data of the target due to noise or uncertainty. In this paper, a Kalman filter is used as a tracking filter in a simulated target-interceptor scenario with noise. It estimates the position, velocity, and acceleration of the target in the presence of noise. These estimations are needed for both proportional navigation and differential geometry guidance laws. A Kalman filter has a good performance at low noise, but a large noise causes considerable errors leads to performance degradation. Therefore, a new technique is required to overcome this defect using tuning factors to tune a Kalman filter to adapt increasing of noise. The values of the tuning factors are between 0.8 and 1.2, they have a specific value for the first half of range and a different value for the second half. they are multiplied by the estimated values. These factors have its optimum values and are altered with the change of the target heading. A genetic algorithm updates these selections to increase the maximum effective range which was previously reduced by noise. The results show that the selected factors have other benefits such as decreasing the minimum effective range that was increased earlier due to noise. In addition to, the selected factors decrease the miss distance for all ranges of this direction of the target, and expand the effective range which leads to increase probability of kill.

Keywords: proportional navigation, differential geometry, Kalman filter, genetic algorithm

Procedia PDF Downloads 510

Authors: S. Gherbi, F. Bouchareb

Abstract:

This paper deals with the novel intelligent bio-inspired control strategies, it presents a novel approach based on an optimal fuzzy immune PID parameters tuning, it is a combination of a PID controller, inspired by the human immune mechanism with fuzzy logic. Such controller offers more possibilities to deal with the delayed systems control difficulties due to the delay term. Indeed, we use an optimization approach to tune the four parameters of the controller in addition to the fuzzy function; the obtained controller is implemented in a modified Smith predictor structure, which is well known that it is the most efficient to the control of delayed systems. The application of the presented approach to control a three tank delay system shows good performances and proves the efficiency of the method.

Keywords: delayed systems, fuzzy immune PID, optimization, Smith predictor

Procedia PDF Downloads 432

Authors: Aman Sharma, Sonali Sengupta

Abstract:

The study explores the utility of Bayesian optimization in tuning the physical and chemical parameters of reactions in an offline experimental setup. A comparative analysis of the influence of the acquisition function on the optimization performance is also studied. For proxy first and second-order reactions, the results are indifferent to the acquisition function used, whereas, while studying the parameters for oxidative desulphurization of thiophene in an offline setup, upper confidence bound (UCB) provides faster convergence along with a marginal trade-off in the maximum conversion achieved. The work also demarcates the critical number of independent parameters and input observations required for both sequential and offline reaction setups to yield tangible results.

Keywords: acquisition function, Bayesian optimization, desulfurization, kinetics, thiophene

Procedia PDF Downloads 182

Authors: Zafer Yüce, Paşa Yayla, Alev Taşkın

Abstract:

There are heaps of analytical methods to estimate the crack growth life of a component. Soft computing methods have an increasing trend in predicting fatigue life. Their ability to build complex relationships and capability to handle huge amounts of data are motivating researchers and industry professionals to employ them for challenging problems. This study focuses on soft computing methods, especially random forest regressors and artificial neural networks with hyperparameter optimization algorithms such as grid search and random grid search, to estimate the crack growth life of an aircraft wing splice joint under variable amplitude loading. TensorFlow and Scikit-learn libraries of Python are used to build the machine learning models for this study. The material considered in this work is 7050-T7451 aluminum, which is commonly preferred as a structural element in the aerospace industry, and regarding the crack type; corner crack is used. A finite element model is built for the joint to calculate fastener loads and stresses on the structure. Since finite element model results are validated with analytical calculations, findings of the finite element model are fed to AFGROW software to calculate analytical crack growth lives. Based on Fighter Aircraft Loading Standard for Fatigue (FALSTAFF), 90 unique fatigue loading spectra are developed for various load levels, and then, these spectrums are utilized as inputs to the artificial neural network and random forest regression models for predicting crack growth life. Finally, the crack growth life predictions of the machine learning models are compared with analytical calculations. According to the findings, a good correlation is observed between analytical and predicted crack growth lives.

Keywords: aircraft, fatigue, joint, life, optimization, prediction.

Procedia PDF Downloads 175

Authors: Mohammad Arif Sobhan Bhuiyan, Zainal Abidin Nordin, Mamun Bin Ibne Reaz

Abstract:

A compact and power efficient high performance Voltage Controlled Oscillator (VCO) is a must in analog and digital circuits especially in the communication system, but the best trade-off among the performance parameters is a challenge for researchers. In this paper, a design of a compact 3-stage differential voltage controlled ring oscillator (VCRO) with low phase noise, low power and higher tuning bandwidth is proposed in 0.18 µm CMOS technology. The VCRO is designed with symmetric load and positive feedback techniques to achieve higher gain and minimum delay. The proposed VCRO can operate at tuning range of 3.9-5.0 GHz at 1.6 V supply voltage. The circuit consumes only 1.0757 mW of power and produces -129 dbc/Hz. The total active area of the proposed VCRO is only 11.74 x 37.73 µm2. Such a VCO can be the best choice for compact and low-power RF applications.

Keywords: CMOS, VCO, VCRO, oscillator

Procedia PDF Downloads 473

Authors: Le Hieu Giang, Truong Nguyen Luan Vu, Le Linh

Abstract:

In this paper, the analytical tuning rules of IMC-PID controller are presented for the multivariable Smith predictor that involved the ideal decoupling. Accordingly, the decoupler is first introduced into the multivariable Smith predictor control system by a well-known approach of ideal decoupling, which is compactly extended for general nxn multivariable processes and the multivariable Smith predictor controller is then obtained in terms of the multiple single-loop Smith predictor controllers. The tuning rules of PID controller in series with filter are found by using Maclaurin approximation. Many multivariable industrial processes are employed to demonstrate the simplicity and effectiveness of the presented method. The simulation results show the superior performances of presented method in compared with the other methods.

Keywords: ideal decoupler, IMC-PID controller, multivariable smith predictor, Padé approximation

Procedia PDF Downloads 419

Authors: Xiaojie Jiang, Wei Cai, Yinxiao Xiang, Ni Zhang, Mengxin Ren, Xinzheng Zhang, Jingjun Xu

Abstract:

Reflection phase of graphene plasmons (GPs) at an abrupt interface is very important, which determines the plasmon resonance of graphene structures of deep sub-wavelength scales. However, at an abrupt graphene edge, the reflection phase is always a constant, ΦR ≈ π/4. In this work, we show that the reflection phase of GPs can be efficiently changed through substrate design. Reflection phase of graphene plasmons (GPs) at an abrupt interface is very important, which determines the plasmon resonance of graphene structures of deep sub-wavelength scales. However, at an abrupt graphene edge, the reflection phase is always a constant, ΦR ≈ π/4. In this work, we show that the reflection phase of GPs can be efficiently changed through substrate design. Specifically, the reflection phase is no longer π/4 at the interface formed by placing a graphene sheet on different substrates. Moreover, tailorable reflection phase of GPs up to 2π variation can be further achieved by scattering GPs at a junction consisting of two such dielectric interfaces with various gap width acting as a Fabry-Perot cavity. Besides, the evolution of plasmon mode in graphene ribbons based on the interface reflection phase tuning is predicted, which is expected to be observed in near-field experiments with scattering-type scanning near-field optical microscopy (s-SNOM). Our work provides another way for in-plane plasmon control, which should find applications for integrated plasmon devices design using graphene.Specifically, the reflection phase is no longer π/4 at the interface formed by placing a graphene sheet on different substrates. Moreover, tailorable reflection phase of GPs up to 2π variation can be further achieved by scattering GPs at a junction consisting of two such dielectric interfaces with various gap width acting as a Fabry-Perot cavity. Besides, the evolution of plasmon mode in graphene ribbons based on the interface reflection phase tuning is predicted, which is expected to be observed in near-field experiments with scattering-type scanning near-field optical microscopy (s-SNOM). Our work provides a new way for in-plane plasmon control, which should find applications for integrated plasmon devices design using graphene.

Keywords: graphene plasmons, reflection phase tuning, plasmon mode tuning, Fabry-Perot cavity

Procedia PDF Downloads 151

Authors: Tolulope Aremu

Abstract:

The key process steps to produce liquid detergent products will introduce potential defects, such as formulation, mixing, filling, and packaging, which might compromise product quality, consumer safety, and operational efficiency. Real-time identification and characterization of such defects are of prime importance for maintaining high standards and reducing waste and costs. Usually, defect detection is performed by human inspection or rule-based systems, which is very time-consuming, inconsistent, and error-prone. The present study overcomes these limitations in dealing with optimization in defect characterization within the process for making liquid detergents using Machine Learning algorithms. Performance testing of various machine learning models was carried out: Support Vector Machine, Decision Trees, Random Forest, and Convolutional Neural Network on defect detection and classification of those defects like wrong viscosity, color deviations, improper filling of a bottle, packaging anomalies. These algorithms have significantly benefited from a variety of optimization techniques, including hyperparameter tuning and ensemble learning, in order to greatly improve detection accuracy while minimizing false positives. Equipped with a rich dataset of defect types and production parameters consisting of more than 100,000 samples, our study further includes information from real-time sensor data, imaging technologies, and historic production records. The results are that optimized machine learning models significantly improve defect detection compared to traditional methods. Take, for instance, the CNNs, which run at 98% and 96% accuracy in detecting packaging anomaly detection and bottle filling inconsistency, respectively, by fine-tuning the model with real-time imaging data, through which there was a reduction in false positives of about 30%. The optimized SVM model on detecting formulation defects gave 94% in viscosity variation detection and color variation. These values of performance metrics correspond to a giant leap in defect detection accuracy compared to the usual 80% level achieved up to now by rule-based systems. Moreover, this optimization with models can hasten defect characterization, allowing for detection time to be below 15 seconds from an average of 3 minutes using manual inspections with real-time processing of data. With this, the reduction in time will be combined with a 25% reduction in production downtime because of proactive defect identification, which can save millions annually in recall and rework costs. Integrating real-time machine learning-driven monitoring drives predictive maintenance and corrective measures for a 20% improvement in overall production efficiency. Therefore, the optimization of machine learning algorithms in defect characterization optimum scalability and efficiency for liquid detergent companies gives improved operational performance to higher levels of product quality. In general, this method could be conducted in several industries within the Fast moving consumer Goods industry, which would lead to an improved quality control process.

Keywords: liquid detergent manufacturing, defect detection, machine learning, support vector machines, convolutional neural networks, defect characterization, predictive maintenance, quality control, fast-moving consumer goods

Procedia PDF Downloads 18

Authors: Tolulope Aremu

Abstract:

This paper is based on the idea of using deep learning methodology for optimizing production yield by tuning a few key process parameters in a manufacturing environment. The study was explicitly on how to maximize production yield and minimize operational costs by utilizing advanced neural network models, specifically Long Short-Term Memory and Convolutional Neural Networks. These models were implemented using Python-based frameworks—TensorFlow and Keras. The targets of the research are the precision molding processes in which temperature ranges between 150°C and 220°C, the pressure ranges between 5 and 15 bar, and the material flow rate ranges between 10 and 50 kg/h, which are critical parameters that have a great effect on yield. A dataset of 1 million production cycles has been considered for five continuous years, where detailed logs are present showing the exact setting of parameters and yield output. The LSTM model would model time-dependent trends in production data, while CNN analyzed the spatial correlations between parameters. Models are designed in a supervised learning manner. For the model's loss, an MSE loss function is used, optimized through the Adam optimizer. After running a total of 100 training epochs, 95% accuracy was achieved by the models recommending optimal parameter configurations. Results indicated that with the use of RSM and DOE traditional methods, there was an increase in production yield of 12%. Besides, the error margin was reduced by 8%, hence consistent quality products from the deep learning models. The monetary value was annually around $2.5 million, the cost saved from material waste, energy consumption, and equipment wear resulting from the implementation of optimized process parameters. This system was deployed in an industrial production environment with the help of a hybrid cloud system: Microsoft Azure, for data storage, and the training and deployment of their models were performed on Google Cloud AI. The functionality of real-time monitoring of the process and automatic tuning of parameters depends on cloud infrastructure. To put it into perspective, deep learning models, especially those employing LSTM and CNN, optimize the production yield by fine-tuning process parameters. Future research will consider reinforcement learning with a view to achieving further enhancement of system autonomy and scalability across various manufacturing sectors.

Keywords: production yield optimization, deep learning, tuning of process parameters, LSTM, CNN, precision manufacturing, TensorFlow, Keras, cloud infrastructure, cost saving

Procedia PDF Downloads 29

Authors: Pasala Gopi, P. Linga Reddy

Abstract:

The response of the load frequency control problem in an multi-area interconnected electrical power system is much more complex with increasing size, changing structure and increasing load. This paper deals with Load Frequency Control of three area interconnected Power system incorporating Reheat, Non-reheat and Reheat turbines in all areas respectively. The response of the load frequency control problem in an multi-area interconnected power system is improved by designing PID controller using different tuning techniques and proved that the PID controller which was designed by Simulink Design Optimization (SDO) Software gives the superior performance than other controllers for step perturbations. Finally the robustness of controller was checked against system parameter variations

Keywords: load frequency control, pid controller tuning, step load perturbations, inter connected power system

Procedia PDF Downloads 644

Authors: Mohammad Abu-Shaira, Weishi Shi

Abstract:

Adaptive learning, a commonly employed solution to drift, involves updating predictive models online during their operation to react to concept drifts, thereby serving as a critical component and natural extension for online learning systems that learn incrementally from each example. This paper introduces LSTM-SCCM “Long Short-Term Memory Stream Cruise Control Method”, a drift adaptation-as-a-service framework for online learning. LSTM-SCCM automates drift adaptation through prompt detection, drift magnitude quantification, dynamic hyperparameter tuning, performing shortterm optimization and model recalibration for immediate adjustments, and, when necessary, conducting long-term model recalibration to ensure deeper enhancements in model performance. LSTM-SCCM is incorporated into a suite of cutting-edge online regression models, assessing their performance across various types of concept drift using diverse datasets with varying characteristics. The findings demonstrate that LSTM-SCCM represents a notable advancement in both model performance and efficacy in handling concept drift occurrences. LSTM-SCCM stands out as the sole framework adept at effectively tackling concept drifts within regression scenarios. Its proactive approach to drift adaptation distinguishes it from conventional reactive methods, which typically rely on retraining after significant degradation to model performance caused by drifts. Additionally, LSTM-SCCM employs an in-memory approach combined with the Self-Adjusting Memory (SAM) architecture to enhance real-time processing and adaptability. The framework incorporates variable thresholding techniques and does not assume any particular data distribution, making it an ideal choice for managing high-dimensional datasets and efficiently handling large-scale data. Our experiments, which include abrupt, incremental, and gradual drifts across both low- and high-dimensional datasets with varying noise levels, and applied to four state-of-the-art online regression models, demonstrate that LSTM-SCCM is versatile and effective, rendering it a valuable solution for online regression models to address concept drift.

Keywords: automated drift detection and adaptation, concept drift, hyperparameters optimization, online and adaptive learning, regression

Procedia PDF Downloads 11

Authors: A. E. Dumitriu

Abstract:

The LHCb experiment is situated at one of the four points around CERN’s Large Hadron Collider, being a single-arm forward spectrometer covering 10 mrad to 300 (250) mrad in the bending (non-bending) plane, designed primarily to study particles containing b and c quarks. Each one of LHCb’s sub-detectors specializes in measuring a different characteristic of the particles produced by colliding protons, its significant detection characteristics including a high precision tracking system and 2 ring-imaging Cherenkov detectors for particle identification. The major two topics that I am currently concerned in are: the RIVET project (Robust Independent Validation of Experiment and Theory) which is an efficient and portable tool kit of C++ class library useful for validation and tuning of Monte Carlo (MC) event generator models by providing a large collection of standard experimental analyses useful for High Energy Physics MC generator development, validation, tuning and regression testing and V0 analysis for 2013 LHCb NoBias type data (trigger on bunch + bunch crossing) at √s=2.76 TeV.

Keywords: LHCb physics, RIVET plug-in, RIVET, CERN

Procedia PDF Downloads 428

Authors: Mustafa Alhamdi

Abstract:

Industrial application to classify gamma rays and neutron events is investigated in this study using deep machine learning. The identification using a convolutional neural network and recursive neural network showed a significant improvement in predication accuracy in a variety of applications. The ability to identify the isotope type and activity from spectral information depends on feature extraction methods, followed by classification. The features extracted from the spectrum profiles try to find patterns and relationships to present the actual spectrum energy in low dimensional space. Increasing the level of separation between classes in feature space improves the possibility to enhance classification accuracy. The nonlinear nature to extract features by neural network contains a variety of transformation and mathematical optimization, while principal component analysis depends on linear transformations to extract features and subsequently improve the classification accuracy. In this paper, the isotope spectrum information has been preprocessed by finding the frequencies components relative to time and using them as a training dataset. Fourier transform implementation to extract frequencies component has been optimized by a suitable windowing function. Training and validation samples of different isotope profiles interacted with CdTe crystal have been simulated using Geant4. The readout electronic noise has been simulated by optimizing the mean and variance of normal distribution. Ensemble learning by combing voting of many models managed to improve the classification accuracy of neural networks. The ability to discriminate gamma and neutron events in a single predication approach using deep machine learning has shown high accuracy using deep learning. The paper findings show the ability to improve the classification accuracy by applying the spectrogram preprocessing stage to the gamma and neutron spectrums of different isotopes. Tuning deep machine learning models by hyperparameter optimization of neural network models enhanced the separation in the latent space and provided the ability to extend the number of detected isotopes in the training database. Ensemble learning contributed significantly to improve the final prediction.

Keywords: machine learning, nuclear physics, Monte Carlo simulation, noise estimation, feature extraction, classification

Procedia PDF Downloads 150