Showing papers by "Kishore Bingi published in 2021"

A Survey on the Application of WirelessHART for Industrial Process Monitoring and Control.

Abstract: Industrialization has led to a huge demand for a network control system to monitor and control multi-loop processes with high effectiveness. Due to these advancements, new industrial wireless sensor network (IWSN) standards such as ZigBee, WirelessHART, ISA 100.11a wireless, and Wireless network for Industrial Automation-Process Automation (WIA-PA) have begun to emerge based on their wired conventional structure with additional developments. This advancement improved flexibility, scalability, needed fewer cables, reduced the network installation and commissioning time, increased productivity, and reduced maintenance costs compared to wired networks. On the other hand, using IWSNs for process control comes with the critical challenge of handling stochastic network delays, packet drop, and external noises which are capable of degrading the controller performance. Thus, this paper presents a detailed study focusing only on the adoption of WirelessHART in simulations and real-time applications for industrial process monitoring and control with its crucial challenges and design requirements.

Torque and Temperature Prediction for Permanent Magnet Synchronous Motor Using Neural Networks

Abstract: This paper focuses on developing a torque and stator temperature prediction model for permanent magnet synchronous motors using neural networks. The model can predict torque and four other temperature parameters at the permanent magnet surface, stator's yoke, tooth, and winding. The motor's torque and temperatures are predicted without installing any additional sensors into it. Using the training dataset with Levenberg-Marquardt optimization and Bayesian regularization algorithms, the predicted model has the best performance with the least mean square error and the best $R^{2}$ values. Also, the prediction of testing data shows that the estimated model follows closely with actual values. This is true for all the five output parameters.

An intelligent model to predict the life condition of crude oil pipelines using artificial neural networks

Abstract: Inefficient scheduling of a pipeline system may lead to severe degradation and substantial economic losses. Earlier studies mostly focussed on corrosion and statistical analysis. This study presents a novel approach for the prediction of life conditions and the classification of metal loss (ML) faults for a group of five pipeline sections of a pipeline system. An intelligent model is developed using artificial neural networks. The historical reports are grouped from the oil and gas industry located in Sudan. The results obtained by a proposed intelligent model are found to be satisfactory based on the highest coefficient of determination (R2) and the lowest mean squared error (MSE) values. The model developed with 12 number of hidden neurons accurately predicted the pipeline condition with an overall R2 value of 0.98148, 0.99359, 0.9943, 0.99336, and 0.99084 for the pipeline sections S1, S2, S3, S4, and S5, respectively. A sensitivity analysis has been carried out to understand the interrelationship between the factors affecting pipeline conditions for all sections of a pipeline system. The remaining useful life for all the sections of the pipeline system has been estimated, and a comparative analysis has been conducted in this work. The significant advantage of the present work is that the developed model can estimate the type of ML due to which the pipeline condition would mostly deteriorate. The deterioration profiles of the selected factors considered for this study have been generated, and the assessment scale has been designed. The proposed approach is more valuable in oil and gas industries to avoid unnecessary inspection costs and to plan the maintenance schedule. This study is progressively worthwhile to organize pipeline inspections and rehabilitation necessities.

Modeling and Control of Robotic Manipulators: A Fractional Calculus Point of View

Abstract: This paper deals with the fractional-order modeling, stability analysis and control of robotic manipulators, namely a single flexible link robotic manipulator (SFLRM) and 2DOF Serial Flexible Joint Robotic Manipulator (2DSFJ). The control law is derived using Pole Placement (PP) method. This paper uses Mittag–Leffler function for the analysis of SFLRM in the time domain. The stability analysis of the fractional model is carried in a transformed $${\Omega }$$ -Domain, and from the analysis, it is observed that the response of the fractional model of SFLRM robotic manipulator is stable. The main motive behind this analysis is to understand the fractional behavior of robotic manipulators, and it is well known from literature that most of the real-world systems have their own fractional behavior. Furthermore, a real-time SFLRM and 2DSFJ setups are considered to validate the results obtained and it is found that the control law suggested by PP method improves the settling time of the robotic manipulators.

Prediction of Heart Stroke Using Support Vector Machine Algorithm

Abstract: This paper focuses on developing a prediction model to predict heart stroke using the parameters, namely, age, hypertension, previous heart disease status, average body glucose level, BMI, and smoking status. The prediction model is developed using a support vector machine (SVM) algorithm. Further, the SVM algorithm with various decision boundaries like linear, quadratic, and cubic are also produced. The performance prediction results show that the linear and quadratic SVM has performed better in predicting the heart stoke with greater accuracy values. This is true for both the male and female databases during training and testing.

Design and Analysis of Fractional Filters with Complex Orders

Abstract: This paper focuses on designing a complex fractional differentiator for the order $\alpha+j\beta$ . An approximation technique using curve fitting based iterative algorithm is proposed for the implementation of these differentiators. Furthermore, the development of various complex fractional-order filters, namely low-pass, high-pass, band-pass, and all-pass, is presented. Bode diagrams from the results show that the proposed filters have produced a similar behavior to the conventional and fractional filter. Similarly, Bode diagrams of approximated filters using the proposed technique also confirms the achievement of similar behavior to the traditional and fractional filter. The step response on the process plant also proved that the fractional low-pass filter with complex order accomplished well on filtering the noise signal.

Weather Prediction and Classification Using Neural Networks and k-Nearest Neighbors

Abstract: This paper focuses on developing a weather prediction model to predict temperature and humidity. Further, a classification model is also extended to predict the weather condition using the expected model’s output. The proposed hybrid model can predict the temperature and humidity and forecast future weather conditions. The prediction and classification models are created using neural networks and k-nearest neighbors, respectively. The prediction model’s results have shown the best ability for both the output variables (temperature and humidity) with R2 values close to one and MSE values close to zero. Further, the classification model’s results also showed better execution in classifying the weather conditions with the highest accuracy values.

Chaotic Time Series Prediction Model for Fractional-Order Duffing's Oscillator

Abstract: This paper focuses on developing a prediction model for chaotic behavior in fractional-order Duffing's oscillator using neural networks. The model predicts the change in state variables' values of the oscillator using its past observations obtained by numerically solving the governing equations using the famous Grunwald-Letnikov's approach. Further, a comparison of hold-out and k-fold techniques is made using the Levenberg-Marquardt training algorithm. The results show the best-proposed model's prediction performance with mean square errors (MSE) and R2 values close to zero and one, respectively. In all the cases, the k-fold cross-validation has performed better than hold-out. However, the k-fold method has taken more computational time for training the model as it is trained k-times compared to one time using the hold-out method.

An Improved Arithmetic Optimization Algorithm

Abstract: This paper focuses on developing an improved arithmetic optimization algorithm to achieve better convergence during exploration and exploitation phases. The proposed algorithm has been achieved by incorporating other functions like square, cube, sine, and cosine in the algorithms’ stochastic scaling coefficient. Further, a comparison between the proposed method and the conventional technique is made on various benchmark functions. It is observed from the numerical results is that the proposed algorithm with both sin and cos have performed better concerning mean, best, and standard deviation values. Moreover, on achieving the worst global minima, the proposed algorithm showed better performance for most minor functions. The results also highlight that the proposed algorithm has shown the best performance, especially for higher-dimensional systems.

Curve Fitting-Based Approximation of Fractional Differentiator with Complex Orders

Abstract: This paper is focused on the design of fractional differentiator for complex orders of $\alpha+j\beta$ where $\alpha\in[0,1]$ and $\beta\in\Re$ . Furthermore, for the practical realization of these fractional differentiators of complex orders, curve fitting-based approximation using Sanathanan-Koerner iteration is proposed. The fractional differentiator results with complex orders show that the proposed approximation is effectively handled both positive and negative imaginary parts of the complex orders. Furthermore, the results on fractional-integrator, PID controller, and low pass filter with complex orders show that the proposed technique has produced better approximation for the range $\omega$ in [ $\omega_{l},\omega_{h}$ ]. The results also show that introducing an additional parameter has given more flexibility to obtain its robust performance.

Prediction of Turbidity in Beach Waves Using Nonlinear Autoregressive Neural Networks

Abstract: The principal focus of this paper is to develop a prediction model to predict the turbidity of beach waves. The prediction model is developed using a nonlinear autoregressive neural network model using three input parameters: water temperature, wave height, and wave period. The beach wave turbidity is predicted without installing any additional sensors. The performance of the developed model is evaluated on three beaches in Chicago Park’s district. The proposed model performance showed better tracking ability for all the three considered beaches. The R2 and mean square errors MSE also confirm the best prediction model’s performance for both training and testing.

Design and Implementation of Signal Filtering Techniques on Real-time Pressure Process Plant

Abstract: In all the closed-loop feedback industrial processes, the measured sensor signal from the field environment is directly fed to the controller for processing. These raw signals contain the unwanted stochastic noise from the surroundings, which affects the process and controller performance. These issues can be rectified by employing a suitable filtering technique, and the feedback loop performance can be improved significantly. Hence, this paper aims to propose set-point and noise filtering usage in the process control loop. The proposed filtering technique is compared with the existing conventional methods and implemented over the real-time pressure process plant for performance analysis. Also, the numerical comparison is carried out in terms of the rise time, settling time, and peak overshoot for validation of the proposed approach.

Reliable Prediction Intervals of PV Generation Using Quantile Regression Averaging Approach

Abstract: Probabilistic PV generation forecasts are necessary for the uncertainty management in the long-term planning of power systems with PV integrations. The weather-dependent PV generation makes it a challenging task necessitating a nonparametric approach, such as quantile regression, for obtaining probabilistic forecasts. Here, a quantile regression averaging approach is used to combine the selective point forecasts of autoregressive conditional heteroscedastic model, random forests model, and multiple linear regression model to further enhance the forecast accuracy. The selection of sensible regressors with physical relevance is necessary for the proposed framework. Hence, such theoretically formulated regressors capable of modeling real-world PV generation data collected from the USA are utilized for assessing the efficacy of the proposed quantile regression averaging model. The reliabilities of the prediction intervals of the proposed model is compared with the popular quantile regression forests, the quantile k-nearest neighbors, and the basic quantile regression approaches via widely used performance indices.

Development of Hybrid Algorithm Using Moth-Flame and Particle Swarm Optimization

Abstract: This paper focuses on the development of a hybrid algorithm using moth-flame and particle swarm optimization. The main aim of the proposed algorithm is to improve the conventional moth-flame algorithm's performance for obtaining the faster convergence speed and best global optimal solution. Also, the proposed algorithm is to enhance the performance of particle swarm on getting global searchability. The proposed hybrid optimization algorithm's performance is evaluated on solving the well-known benchmark functions. The results show that the proposed hybrid optimization performed better than conventional moth-flame and particle swarm algorithms to obtain the best optimal solution with faster convergence.

Design and Analysis of Complex Fractional-order PID Controllers

Abstract: This paper is focused on the design of a complex fractional-order differentiator and integrator for the order $\alpha+j\beta$ . Furthermore, for these differentiators and integrators' practical realization, an approximation using a curve fitting-based iterative algorithm is proposed. The design of various complex fractional PID controllers using the proposed differentiator and integrator has been presented. The simulation study results show that the designed controllers with complex orders have produced a steady behavior equivalent to fractional controllers' behavior. The step response characteristics on the process plant also show that the designed controllers performed well in controlling the process.

Design of Adaptive Weighted Whale Optimization Algorithm

Abstract: This paper focuses on developing an adaptive weighted whale optimization algorithm that helps avoid the getting trap at local minima during the convergence. The adaptive weight during each iteration of the algorithm also helps achieve optimal solutions during exploration and exploitation. Further, various adaptive weights, including the chaotic consequences and traditional algorithm, are executed on multiple benchmark functions. The statistical results determined in terms of mean, best and standard deviation depict that the proposed adaptive weighted algorithm performs a higher level than conventional and chaotic weighted algorithms. The results also highlighted that the developed technique showed preferable performance for most minor functions than the traditional technique on achieving the worst global minima.

Bearing Fault Detection in Induction Motors Using Line Currents

Abstract: This paper focuses on the development of a bearing fault detection model for induction motors using line currents. The graphical and numerical analysis of the model has been developed using the park's vector approach and envelope based on the Hilbert transform. The proposed model has been evaluated on currents measured from eight different types of induction motors. The graphical results from the Concordia pattern between d- and q-components of stator currents show that healthy bearing behaviour is circular compared to the faulty bearing's elliptical. The numerical results show that the minimum and maximum envelope of d- and q-components of stator currents is more significant than one. The sum of Kurtosis for the envelope of d- and q-components of stator currents is less than 5.0.

Adaptation of Spiral Radius and Angle in Hypotrochoid Spiral Dynamic Algorithm

Abstract: This paper focuses on developing an adaptation algorithm for hypotrochoid spiral dynamic optimization using linear adaptive spiral radius and angle by dynamically varying the value for each iteration based on the fitness function value. The adaptive algorithm will help obtain the optimal search point compared to fixed radius and angle in conventional methods. The spiral radius and angle effect show that the spiral movement with a negative radius will boost the process of escaping from converging at local optima. The statistical results on various benchmark functions show that the proposed optimization has performed better than spiral dynamic, adaptive spiral dynamic, and hypotrochoid spiral dynamic algorithms.

Development of Exponentially Weighted Sine Cosine Optimization Algorithm

Abstract: This paper focuses on developing an exponentially weighted sine cosine algorithm that helps achieve faster convergence and better global optimal solutions. The proposed algorithm has been achieved by incorporating exponential weight functions in the position updation equations that change during each algorithm iteration. Further, a comparison of the proposed algorithm with the traditional technique is made on various benchmark functions-selecting these functions of multiple categories such as unimodal, multimodal, and composite. The optimization results indicated that the proposed exponentially weighted algorithm performed superior to the traditional and other adaptive weighted algorithms. The best performance is proper for most functions concerning mean, best, and standard deviation values. Moreover, the conventional technique has reached the worst global minima values for most of the test functions than the proposed algorithm.

An Inertia Weight Concept-Based Salp Swarm Optimization Algorithm

Abstract: This paper has introduced an improved salp swarm algorithm based on the inertia weight concept. The inertia weight concept will help achieve better convergence on obtaining a more accurate solution during both exploration and exploitation phases. Further, comparing the algorithm's performance with different inertia weights and the traditional algorithm is also made on various benchmark functions. The numerical results for best, worst, mean, and standard deviation values show that the proposed algorithm shown the best performance than the compared algorithms. The best performance is actual for most of the test cases compared to the traditional technique. Moreover, the conventional algorithm has achieved the worst global minima for the maximum number of test functions.