Online voltage stability monitoring using Artificial Neural Network

Voltage stability has recently become a challenging problem for many power systems. Voltage instability can be ascribed to the lack of reactive power support needed to maintain the voltage profile at a specified value. It has been responsible for severe system disturbances including major blackouts. A key concept in the restructuring of the electric power industry is the ability to accurately and rapidly quantify the capabilities of transmission systems. Computation of available transmission capability (ATC) must take into account adequate static, dynamic, and voltage stability margins. Online voltage stability assessment tools will be required for the secure operation of interconnected power systems. This paper presents the application of artificial neural networks (ANN) for online voltage stability assessment. A key feature of the proposed method is the use of principal component analysis to project the input patterns in the original pattern space into a new subspace having fewer dimensions than the original pattern space. This enhances the efficiency of ANN training. The proposed neural network is used to determine the voltage stability margin of the IEEE 118 bus power system for different operating conditions. The possibility of including topology information in a single ANN is also investigated.

This paper presents an application of Artificial Neural Network (ANN) algorithm for improving power system voltage stability. The training data is obtained by solving several normal and abnormal conditions using the Linear Programming technique. The selected objective function gives minimum deviation of the reactive power control variables, which leads to the maximization of minimum Eigen value of load flow Jacobian. The considered reactive power control variables are switchable VAR compensators, OLTC transformers and excitation of generators. The method has been implemented on a modified IEEE 30-bus test system. The results obtain from the test clearly show that the trained neural network is capable of improving the voltage stability in power system with a high level of precision and speed.

This paper presents a study of the application of artificial neural network (ANN) to the evaluation of the distance to the voltage collapse point. Voltage stability has been of the major concern in power system operation. To prevent these problems, technical staff evaluates frequently the distance of the operation state to the voltage collapse point. This distance normally is calculated with power flow equations. This classic technique is very slow for electric power systems with large dimension. In abnormal exploration situations it may introduce serious limitation in the voltage stability analysis process. So, the application of a fast and reliable evaluation technique is very important to diminish the evaluation time. This paper also presents the method FSQV (Full sum dQ/dV) for the detection of the collapse point.

ANN based evaluation of the NOx concentration in the exhaust gas of a marine two-stroke diesel engineThe article presents results of a study on the possible application of artificial neural networks (ANNs) to the evaluation of NOx concentration in the exhaust gas of a marine two-stroke Diesel engine. A concept is presented how to use the ANN as an alternative to direct measurements carried out on a ship at sea. Methods of proper ANN selection, configuration and training are presented. Also included are the results of laboratory tests, performed to obtain data for ANN training and tests, and the results obtained from modelling certain processes with the aid of selected ANNs. As a result of the performed investigations, an ANN was constructed and trained to calculate NOx concentration in the Diesel engine exhaust gas based on the engine operation parameters measured with an average error of 1.83%, and the fuel consumption measured with an average error of 1.12%.

The identification of voltage collapse (VC) is crucial to prevent a possible collapse of the preventive control actions and voltage security evaluation. Selecting the critical buses in the network can assist in determining the locations where voltage collapses may occur. VC initially manifests at the weakest bus in a serious emergency case. So, for operational and planning purposes, it is essential to detect critical buses in an electric power system. The analysis of the power system in view of voltage stability (VS) was performed under different loading conditions using voltage stability indices (VSIs). The line voltage stability indices in terms of the fast voltage stability index (FVSI) and line stability index (LMN) are utilized in this paper to identify the weakest bus in the network. The suggested procedure is tested on a standard network (IEEE 14-bus system) at different overloading conditions (25 – 100 % overload) utilizing power system analysis toolbox (PSAT) software. The results proved that this index has a higher standard for predicting the point of voltage collapse and identification the weakest bus in the network, so consider more reliable and accurate relative to other indices.

Development and application of reservoir models and artificial neural networks for optimizing ventilation air requirements in development mining of coal seams

This article discusses the applications of Artificial Neural Network (ANN) and Fuzzy Logic Control (FLC) strategies in a control context of a grid connected Wind Energy Conversion System (WECS), using a Doubly-Fed Induction Generator (DFIG). To rigorously explore the performance of the controllers, a systemic approach based on an ideal model and a nominal model of the wind turbine is used for the comparative analysis between PI, FLC and ANN. It turns out that the PI is less efficient than ANN and FLC. It turns out that the PI is less efficient than ANN and FLC. Whereas, for a high level of control, the FLC has better performance than the ANN. For a low level, the performance of the ANN is very slightly superior to the FLC. In addition, one notes a good rejection of disturbance and a good robustness with the FLC compared to the ANN. The latter has a Total Harmonic Distortion (THD) and cos ϕ ≈ 1 slightly better than the FLC. In short, the ANN and FLC present great advantages for the WECS and the results obtained are satisfactory. The platform used for modeling and simulation studies is MATLAB/Simulink.KeywordsWind Energy Conversion SystemFuzzy Logic Control (FLC)Artificial Neural Network (ANN)DFIGPower grid

Artificial neural network enabled accurate geometrical design and optimisation of thermoelectric generator

Many technological advancements in the modern era have made actual use of electrical power and the constrained operating of power systems within stability limits. Some expeditious load variations and rising power demands initiate complications in voltage stability and can put stress on performance, leading to voltage instability. Voltage Stability Indices can be used to perform voltage stability assessment. This review evaluates various VSIs based on mathematical derivations, assumptions, critical values, and methodology. VSIs determine the maximum loadability, voltage collapse proximity, stability margin, weak areas, and contingency ranking. Stability indices can also specify the optimal placing and sizing of Distributed Generators. Thus, VSIs play a vital role in power system voltage stability. This review is a comprehensive survey of various indices and analyses their accuracy in determining the instability of power systems. Voltage stability is a crucial concern in operating a reliable power system, and the systematic evaluation of voltage stability is essential in a power system. This review considered and analyzed 34 indices from 138 articles from the literature for their significant performance in various power system stability problems. Of 33 indices, were 22 derived from transmission line parameters, referred to as line indices, and 12 from bus and line parameters, referred to as bus indices.

The paper presents an innovative method for smoothing fluctuations of heat flux, using the thermal energy storage unit (TES Unit) with phase change material and Artificial Neural Networks (ANN) control. The research was carried out on a pilot large-scale installation, of which the main component was the TES Unit with a heat capacity of 500 MJ. The main challenge was to smooth the heat flux fluctuations, resulting from variable heat source operation. For this purpose, a molten salt phase change material was used, for which melting occurs at nearly constant temperature. To enhance the smoothing effect, a classical control system based on PID controllers was supported by ANN. The TES Unit was supplied with steam at a constant temperature and variable mass flow rate, while a discharging side was cooled with water at constant mass flow rate. It was indicated that the operation of the TES Unit in the phase change temperature range allows to smooth the heat flux fluctuations by 56%. The tests have also shown that the application of artificial neural networks increases the smoothing effect by 84%.

<abstract><p>The training of artificial neural networks (ANNs) with rectified linear unit (ReLU) activation via gradient descent (GD) type optimization schemes is nowadays a common industrially relevant procedure. GD type optimization schemes can be regarded as temporal discretization methods for the gradient flow (GF) differential equations associated to the considered optimization problem and, in view of this, it seems to be a natural direction of research to <italic>first aim to develop a mathematical convergence theory for time-continuous GF differential equations</italic> and, thereafter, to aim to extend such a time-continuous convergence theory to implementable time-discrete GD type optimization methods. In this article we establish two basic results for GF differential equations in the training of fully-connected feedforward ANNs with one hidden layer and ReLU activation. In the first main result of this article we establish in the training of such ANNs under the assumption that the probability distribution of the input data of the considered supervised learning problem is absolutely continuous with a bounded density function that every GF differential equation admits for every initial value a solution which is also unique among a suitable class of solutions. In the second main result of this article we prove in the training of such ANNs under the assumption that the target function and the density function of the probability distribution of the input data are piecewise polynomial that every non-divergent GF trajectory converges with an appropriate rate of convergence to a critical point and that the risk of the non-divergent GF trajectory converges with rate 1 to the risk of the critical point. We establish this result by proving that the considered risk function is <italic>semialgebraic</italic> and, consequently, satisfies the <italic>Kurdyka-Łojasiewicz inequality</italic>, which allows us to show convergence of every non-divergent GF trajectory.</p></abstract>

An Artificial Neural Network (ANN) is an information processing paradigm that is inspired by the way biological nervous systems, such as the brain, process information. The key element of this paradigm is the novel structure of the information processing system. It is composed of a large number of highly interconnected processing elements (neurones) working in unison to solve specific problems. ANNs, like people, learn by example. An ANN is configured for a specific application, such as pattern recognition or data classification, through a learning process. Learning in biological systems involves adjustments to the synaptic connections that exist between the neurones. The ANN has recently been applied in process control, identification, diagnostics, character recognition, sensory prediction, robot vision, and forecasting. In Textiles and Clothing industries, it involves the interaction of a large number of variables. Because of the high degree of variability in raw materials, multistage processing and a lack of precise control on process parameters, the relation between such variables and the product properties is relied on the human knowledge but it is not possible for human being to remember all the details of the process-related data over the years. As the computing power has substantially improved over last decade, the ANN is able to learn such datasets to reveal the unknown relation between various variables effectively. Therefore, the application of ANN is more widespread in textiles and clothing industries over last decade. In this chapter, it aims to review current application of ANN in textiles and clothing industries over last decade. Based on literature reviews, the challenges encountered by ANN used in the industries will be discussed and the potential future application of ANN in the industries will also be addressed. The structure of this chapter comprises of seven sections. The first section includes background of ANN, importance of ANN in textiles and clothing and the arrangement of this chapter. In forthcoming three sections, they include review of applications of ANN in fibres and yarns, in chemical processing, and in clothing over last decade. Afterwards, challenges encountered by ANN used in textiles and clothing industries will be discussed and potential future application of ANN in textiles and clothing industries will be addressed in last section.

This paper investigates the application of Artificial Neural Networks (ANNs) for structural data augmentation, using welded beam-to-column steel joints as a representative case study within a broader research effort aimed at improving the reliability-based design of ductile steel joints. While simplified design methods such as the component method are widely adopted, they often underestimate joint resistance in ductile failure scenarios, limiting the exploitation of the full resistance and deformation capacity of steel joints. To develop improved resistance criteria and satisfy the target reliability levels defined in EN 1990, a large volume of high-fidelity structural data is required, making traditional experimental and finite element (FE) approaches computationally unfeasible for Monte Carlo simulations. As a preliminary step, this study evaluates the performance of ANNs trained on deterministic (nominal) input data derived from a validated FEM database of 2,400 welded joint configurations, enabling efficient prediction of initial stiffness and moment resistance. A second investigation then assesses the ANN's capacity to generalize when applied to stochastically varied input parameters, as required for probabilistic applications. Results show that deterministic-trained models underperform in this setting, underscoring the need for tailored training strategies. While this paper establishes a robust ANN-based methodology for deterministic modeling, it also sets the stage for future work on stochastic ANN training and reliability-based joint assessment.

Voltage Stability Indicators (VSI) play a significant role in determining the voltage stability of the power system. In order to forecast the voltage instability of the system using voltage stability indicators, this paper presents an implementation of an Artificial Neural Network (ANN) based on the Levenberg–Marquardt (LM) technique. In this context, the performance of three voltage stability indicators – the Line Voltage Stability Index (LVSI), the Line stability index (Lmn), and the Fast Voltage Stability Indicator (FVSI) are compared. Based on the maximum active power loadability of load buses of the IEEE 14-bus and IEEE 118-bus systems, these indicators are used to assess their vulnerability. The LVSI, Lmn, and FVSI indices obtained from the Newton-Raphson method of the most severe buses of both test systems are compared with the forecasted values by the ANN method under base load to critical loading conditions. The real and reactive power losses of the lines associated with the most severe bus of the systems and totally real and reactive power losses of the systems are forecasted by the MATLAB NN toolbox under wide variations in active power loading. The Static Synchronous Compensator (STATCOM) is used to enhance the voltage of the most severe bus of the system. The outcomes show that the methods for assessing voltage stability using ANN under the variation of the real power demand of the critical bus is highly précised and technically feasible.

Training of artificial neural networks using the experimental data obtained in the process of drying of cotton powdered cellulose (CPC), have shown that, experiments can be conducted on the computers, which solves many of the practical and ethical issues. Therefore, arose and remain at the present time, the objective of neural simulation of processes and create a computing system (artificial neural network)