Comparison of cascade P-PI controller tuning methods for PMDC motor based on intelligence techniques

In this paper, there are two contributions: The first contribution is to design a robust cascade P-PI controller to control the speed and position of the permanent magnet DC motor (PMDC). The second contribution is to use three methods to tuning the parameter values for this cascade controller by making a comparison between them to obtain the best results to ensure accurate tracking trajectory on the axis to reach the desired position. These methods are the classical method (CM) and it requires some assumptions, the genetic algorithm (GA), and the particle swarm optimization algorithm (PSO). The simulation results show the system becomes unstable after applying the load when using the classical method because it assumes cancellation of the load effect. Also, an overshoot of about 3.763% is observed, and a deviation from the desired position of about 12.03 degrees is observed when using the GA algorithm, while no deviation or overshoot is observed when using the PSO algorithm. Therefore, the PSO algorithm has superiority as compared to the other two methods in improving the performance of the PMDC motor by extracting the best parameters for the cascade P-PI controller to reach the desired position at a regular speed.

A Review of Recent Developments in Autotuning Methods for Fractional-Order Controllers

The scientific community has recently seen a fast-growing number of publications tackling the topic of fractional-order controllers in general, with a focus on the fractional order PID. Several versions of this controller have been proposed, including different tuning methods and implementation possibilities. Quite a few recent papers discuss the practical use of such controllers. However, the industrial acceptance of these controllers is still far from being reached. Autotuning methods for such fractional order PIDs could possibly make them more appealing to industrial applications, as well. In this paper, the current autotuning methods for fractional order PIDs are reviewed. The focus is on the most recent findings. A comparison between several autotuning approaches is considered for various types of processes. Numerical examples are given to highlight the practicality of the methods that could be extended to simple industrial processes.

Vinay Mishra and the Artistry of the Harmonium

Vinay Mishra is an accomplished Indian solo and accompanying harmonium player born and brought up in Benaras and currently residing in Delhi serving as a faculty member of the Department of Music, Faculty of Music and Fine Arts, University of Delhi. The rigorous training of both vocal and instrumental music under veteran Hindustani Music virtuosos, the academic and scholarly scope built up till the degree of PhD in Music, the realizations, and understandings on music must have conspicuously made an impact of his practice and artistry as a harmonium player. Harmonium was originated in the west and adopted by Indian musicians in the colonial era which was brought up to the present day through many artistic, cultural and political controversies, and obstacles. This work focuses on discovering the insights of the harmonium art of Vinay Mishra. Hence, his academic background, musical training, musical career, his playing style as a soloist, general techniques and techniques of accompaniment, sense of machinery, perspectives on raga Taal, and thoroughly the tuning methods were studied in-depth through personal conversations and literature resources where it was observed that modern Hindustani harmonium artists favor a typical natural tuning method over the 12 equal temperaments of the common keyboard instruments. According to him, the stable sound of the harmonium was the reason to be vocal music- friendly in classical and light vocal music accompaniment which was only interrupted by the equal temperament earlier and was later overcome by the artists and harmonium makers. The idea was also raised that apart from gaining the basic command of an instrument, a Hindustani instrumentalist may learn and practice all other aspects of Hindustani music from the teachers of other forms too. Vinay Mishra’s thoughts of machinery, musical forms, compositions, applying Hindustani vocal, and plucking string instrumental ornamentations on the Harmonium were also reviewed.

Energy demand prediction with machine learning supported by auto-tuning: a case study

The operational energy of buildings is making up one of the highest proportions of life-cycle carbon emissions. A more efficient operation of facilities would result in significant energy savings but necessitates computational models to predict a building’s future energy demands with high precision. To this end, various machine learning models have been proposed in recent years. These models’ prediction accuracies, however, strongly depend on their internal structure and hyperparameters. The time demand and expertise required for their finetuning call for a more efficient solution. In the context of a case study, this paper describes the relationship between a machine learning model’s prediction accuracy and its hyperparameters. Based on time-stamped recordings of outdoor temperatures and electricity demands of a hospital in Japan, recorded every 30 minutes for more than four years, using a deep neural network (DNN) ensemble model, electricity demands were predicted for sixty time steps to follow. Specifically, we used automatic hyperparameter tuning methods, such as grid search, random search, and Bayesian optimization. A single time step ahead, all tuning methods reduced the RSME to less than 50%, compared to non-optimized tuning. The results attest to machine learning models’ reliance on hyperparameters and the effectiveness of their automatic tuning.

Soft Computing Based Tuning of PI Controller With Cuckoo Search Optimization For Level Control of Hopper Tank System

The paper work focuses on soft computing and Conventional tuning approach to design of PI controller, which provides a better sustainable performance for a nonlinear hopper tank system which is used in Wastewater treatment applications. The system processes the combination of a conical and cylindrical tank for providing Multi-region based mathematical modelling to obtain the first order with delay time (FOPDT) process transfer function model. The Ziegler Nichols, Cohen-coon, Tyreus Luben, CHR (Chien, Hrones, and Reswick), IMC (Internal Model Control), Direct Synthesis, FOPI( Fractional Order PI) Conventional tuning formulae and Cuckoo Search Optimization (CSO) algorithm are used to optimize the servo regulatory responses of PI controller. The integral and proportional gain of the PI controller is said to produce the fastest settling time and reduces the error using performance indices and achieves Liquid Level control in hopper tank. Comparison is made for the various conventional controller tuning methods with Cuckoo Search Optimization tuning responses and identified to CSO-PI method offers enhanced Optimized Performance while comparing to Conventional tuning methods for a region based system.

An Improved Multiple Features and Machine Learning-Based Approach for Detecting Clickbait News on Social Networks

The widespread usage of social media has led to the increasing popularity of online advertisements, which have been accompanied by a disturbing spread of clickbait headlines. Clickbait dissatisfies users because the article content does not match their expectation. Detecting clickbait posts in online social networks is an important task to fight this issue. Clickbait posts use phrases that are mainly posted to attract a user’s attention in order to click onto a specific fake link/website. That means clickbait headlines utilize misleading titles, which could carry hidden important information from the target website. It is very difficult to recognize these clickbait headlines manually. Therefore, there is a need for an intelligent method to detect clickbait and fake advertisements on social networks. Several machine learning methods have been applied for this detection purpose. However, the obtained performance (accuracy) only reached 87% and still needs to be improved. In addition, most of the existing studies were conducted on English headlines and contents. Few studies focused specifically on detecting clickbait headlines in Arabic. Therefore, this study constructed the first Arabic clickbait headline news dataset and presents an improved multiple feature-based approach for detecting clickbait news on social networks in Arabic language. The proposed approach includes three main phases: data collection, data preparation, and machine learning model training and testing phases. The collected dataset included 54,893 Arabic news items from Twitter (after pre-processing). Among these news items, 23,981 were clickbait news (43.69%) and 30,912 were legitimate news (56.31%). This dataset was pre-processed and then the most important features were selected using the ANOVA F-test. Several machine learning (ML) methods were then applied with hyper-parameter tuning methods to ensure finding the optimal settings. Finally, the ML models were evaluated, and the overall performance is reported in this paper. The experimental results show that the Support Vector Machine (SVM) with the top 10% of ANOVA F-test features (user-based features (UFs) and content-based features (CFs)) obtained the best performance and achieved 92.16% of detection accuracy.

Design of voltage and current controller parameters using small signal model-based pole-zero cancellation method for improved transient response in microgrids

Microgrids are supposed to provide stable power for seamless utility-grid interaction under all conditions as stated by IEEE-1547 standard. But, the use of power electronic inverter makes the microgrid sensitive to transients than synchronous generator-based plants. This degrades the voltage/frequency responses during transients, which can lead to transient stability problem if not controlled properly. Hence, the design of effective closed-loop voltage and current (V/I) controllers is highly desired to control the inverter output against the disturbances. The V/I controllers are based on PI (proportional-cum-integral) formulas. Thus, the effectiveness of V/I controllers relies on how accurate that their gain parameters are tuned. Many PI-tuning methods have been developed in the literature, but, it is yet difficult to identify a suitable method for an application. Also, only a few researchers have focused on the microgrids due to the complexity involved in its controller design by the presence of V/I cascaded dual-loop. Hence, to address this problem, this paper proposes a novel way of designing V/I controller parameters by using pole-zero cancellation method. This method is implemented by deriving the microgrid’s small-signal model. This improves the transient response through reduced system order and/or alleviated sluggish/marginal-stable/unstable poles by adding zeros at same places where those poles are laid, to in effect cancel them. The efficacy of the proposed method over existing methods is assessed by plotting frequency and voltage responses under different test conditions. From the simulation results, it is witnessed that the proposed method relatively improved the transient characteristics of microgrids. Article Highlights Analyzes the applicability of conventional PI tuning methods for microgrid controllers’ design. Proposes a novel small signal model based pole-zero cancellation method for the design of microgrid controllers. Enhances the gain margin, which improves the stabilization capacity of the system when subjected to disturbances. Improves the transient behavior of frequency and voltage responses, which ensure the safety of sensitive loads.

Cross-Validation, Information Theory, or Maximum Likelihood? A Comparison of Tuning Methods for Penalized Splines

Functional data analysis techniques, such as penalized splines, have become common tools used in a variety of applied research settings. Penalized spline estimators are frequently used in applied research to estimate unknown functions from noisy data. The success of these estimators depends on choosing a tuning parameter that provides the correct balance between fitting and smoothing the data. Several different smoothing parameter selection methods have been proposed for choosing a reasonable tuning parameter. The proposed methods generally fall into one of three categories: cross-validation methods, information theoretic methods, or maximum likelihood methods. Despite the well-known importance of selecting an ideal smoothing parameter, there is little agreement in the literature regarding which method(s) should be considered when analyzing real data. In this paper, we address this issue by exploring the practical performance of six popular tuning methods under a variety of simulated and real data situations. Our results reveal that maximum likelihood methods outperform the popular cross-validation methods in most situations—especially in the presence of correlated errors. Furthermore, our results reveal that the maximum likelihood methods perform well even when the errors are non-Gaussian and/or heteroscedastic. For real data applications, we recommend comparing results using cross-validation and maximum likelihood tuning methods, given that these methods tend to perform similarly (differently) when the model is correctly (incorrectly) specified.