Universal Approximation Using Radial-Basis-Function Networks

A new hybrid force/position control approach for time-varying constrained reconfigurable manipulators

In this manuscript, a new hybrid force/position control approach has been proposed for time-varying constrained reconfigurable manipulators. In order to design the controller, firstly a reduced-order dynamic model of time-varying constrained manipulator system is presented. The uncertainties in the dynamical model of the system are inevitable; therefore the model-based control approach is inadequate to handle these systems. Therefore, inspired by this consideration, whatsoever partial information is available about the dynamics of the system, have been used for controller design purpose. The model-dependent control scheme is integrated with the neural network-based model-free control scheme. Radial basis function neural network is used for the estimation of the unknown dynamics of the system. Next, to overcome the aftereffects of the friction terms and neural network reconstruction error, an adaptive compensator is added to the part of the controller. For the stability analysis of the presented control scheme, the Lyapunov theorem and Barbalat's lemma are utilized. The designed control scheme guarantees that tracking errors of the joints and the force tracking error remain inside the desired levels and the joint tracking errors converge to zero asymptotically. Finally, comparative computer simulations show the superiority and the applicability of the developed control method applied over a 2-DOF time-varying constrained reconfigurable manipulator.

Small Fault Detection of Discrete-Time Nonlinear Uncertain Systems

This article investigates the problem of small fault detection (sFD) for discrete-time nonlinear systems with uncertain dynamics. The faults are considered to be "small" in the sense that the system trajectories in the faulty mode always remain close to those in the normal mode, and the magnitude of fault can be smaller than that of the system's uncertain dynamics. A novel adaptive dynamics learning-based sFD framework is proposed. Specifically, an adaptive dynamics learning approach using radial basis function neural networks (RBF NNs) is first developed to achieve locally accurate identification of the system uncertain dynamics, where the obtained knowledge can be stored and represented in terms of constant RBF NNs. Based on this, a novel residual system is designed by incorporating a newmechanism of absolute measurement of system dynamics changes induced by small faults. An adaptive threshold is then developed for real-time sFD decision making. Rigorous analysis is performed to derive the detectability condition and the analytical upper bound for sFD time. Simulation studies, including an application to a three-tank benchmark engineering system, are conducted to demonstrate the effectiveness and advantages of the proposed approach.

Gap Filling for Historical Landsat NDVI Time Series by Integrating Climate Data

High-quality Normalized Difference Vegetation Index (NDVI) time series are essential in studying vegetation phenology, dynamic monitoring, and global change. Gap filling is the most important issue in reconstructing NDVI time series from satellites with high spatial resolution, e.g., the Landsat series and Chinese GaoFen-1/6 series. Due to the sparse revisit frequencies of high-resolution satellites, traditional reconstruction approaches face the challenge of dealing with large gaps in raw NDVI time series data. In this paper, a climate incorporated gap-filling (CGF) method is proposed for the reconstruction of Landsat historical NDVI time series data. The CGF model considers the relationship of the NDVI time series and climate conditions between two adjacent years. Climate variables, including downward solar shortwave radiation, precipitation, and temperature, are used to characterize the constrain factors of vegetation growth. Radial basis function networks (RBFNs) are used to link the NDVI time series between two adjacent years with variabilities in climatic conditions. An RBFN predicted a background NDVI time series in the target year, and the observed NDVI values in this year were used to adjust the predicted NDVI time series. Finally, the NDVI time series were recursively reconstructed from 2018 to 1986. The experiments were performed in a heterogeneous region in the Qilian Mountains. The results demonstrate that the proposed method can accurately reconstruct and generate continuous 30 m 8-day NDVI time series using Landsat observations. The CGF method outperforms traditional time series reconstruction methods (e.g., the harmonic analysis of time series (HANTS) and Savitzky-Golay (SG) filter methods) when the raw time series is contaminated with large gaps, which widely exist in Landsat images.

Quantitative Spectral Data Analysis Using Extreme Learning Machines Algorithm Incorporated with PCA

Extreme learning machine (ELM) is a popular randomization-based learning algorithm that provides a fast solution for many regression and classification problems. In this article, we present a method based on ELM for solving the spectral data analysis problem, which essentially is a class of inverse problems. It requires determining the structural parameters of a physical sample from the given spectroscopic curves. We proposed that the unknown target inverse function is approximated by an ELM through adding a linear neuron to correct the localized effect aroused by Gaussian basis functions. Unlike the conventional methods involving intensive numerical computations, under the new conceptual framework, the task of performing spectral data analysis becomes a learning task from data. As spectral data are typical high-dimensional data, the dimensionality reduction technique of principal component analysis (PCA) is applied to reduce the dimension of the dataset to ensure convergence. The proposed conceptual framework is illustrated using a set of simulated Rutherford backscattering spectra. The results have shown the proposed method can achieve prediction inaccuracies of less than 1%, which outperform the predictions from the multi-layer perceptron and numerical-based techniques. The presented method could be implemented as application software for real-time spectral data analysis by integrating it into a spectroscopic data collection system.

An Investigation of Radial Basis Function Method for Strain Reconstruction by Energy-Resolved Neutron Imaging

The main objective of the current work is to determine meshless methods using the radial basis function (rbf) approach to estimate the elastic strain field from energy-resolved neutron imaging. To this end, we first discretize the longitudinal ray transformation with rbf methods to give us an unconstrained optimization problem. This discretization is then transformed into a constrained optimization problem by adding equilibrium conditions to ensure uniqueness. The efficiency and accuracy of this approach are investigated for the situation of 2d plane stress. In addition, comparisons are made between the results obtained with rbf collocation, finite-element (fem) and analytical solution methods for test problems. The method is then applied to experimentally measured continuous and discontinuous strain fields using steel samples for an offset ring-and-plug and crushed ring, respectively.

Chemical formula input relied intelligent identification of an inorganic perovskite for solar thermochemical hydrogen production

An efficient prediction procedure based on the random forest method is developed for the intelligent identification of pure and doped perovskites for solar thermochemical H₂ production.

Gradient-based training and pruning of radial basis function networks with an application in materials physics

Many applications, especially in physics and other sciences, call for easily interpretable and robust machine learning techniques. We propose a fully gradient-based technique for training radial basis function networks with an efficient and scalable open-source implementation. We derive novel closed-form optimization criteria for pruning the models for continuous as well as binary data which arise in a challenging real-world material physics problem. The pruned models are optimized to provide compact and interpretable versions of larger models based on informed assumptions about the data distribution. Visualizations of the pruned models provide insight into the atomic configurations that determine atom-level migration processes in solid matter; these results may inform future research on designing more suitable descriptors for use with machine learning algorithms.

Leveraging machine learning for predicting human body model response in restraint design simulations

The objective of this study was to leverage and compare multiple machine learning techniques for predicting the human body model response in restraint design simulations. Parametric simulations with 16 independent variables were performed. Ordinary least-squares (OLS), least absolute shrinkage and selection operator (LASSO), neural network (NN), support vector regression (SVR), regression forest (RF), and an ensemble method were used to develop response surface models of the simulations. The hyperparameters of the machine learning techniques were optimized through grid search and cross-validation to avoid under-fitting and over-fitting. The ensemble method outperformed other techniques, followed by LASSO, SVR, NN, RF, and OLS. Findings indicated that optimizing the metamodel hyper-parameters are essential to predict the optimum set of restraint design parameters.

An Exact Reformulation of Feature-Vector-Based Radial-Basis-Function Networks for Graph-Based Observations

Radial basis function (RBF) networks are traditionally defined for sets of vector-based observations. In this brief, we reformulate such networks so that they can be applied to adjacency-matrix representations of weighted, directed graphs that represent the relationships between object pairs. We restate the sum-of-squares objective function so that it is purely dependent on entries from the adjacency matrix. From this objective function, we derive a gradient descent update for the network weights. We also derive a gradient update that simulates the repositioning of the radial basis prototypes and changes in the radial basis prototype parameters. An important property of our radial basis function networks is that they are guaranteed to yield the same responses as conventional radial basis networks trained on a corresponding vector realization of the relationships encoded by the adjacency matrix. Such a vector realization only needs to provably exist for this property to hold, which occurs whenever the relationships correspond to distances from some arbitrary metric applied to a latent set of vectors. We, therefore, completely avoid needing to actually construct vectorial realizations via multidimensional scaling, which ensures that the underlying relationships are totally preserved.

A Sensorless Wind Speed and Rotor Position Control of PMSG in Wind Power Generation Systems

Currently, among the topologies of wind energy conversion systems, those based on full power converters are growing. The permanent magnet synchronous generator (PMSG) uses full power converter to allow wide speed ranges to extract the maximum power from the wind. In order to obtain efficient vector control in a synchronous generator with permanent magnets, it is necessary to know the position of the rotor. The PMSGs work over a wide range of speed, and it is mandatory to measure or estimate their speed and position. Usually, the position of the rotor is obtained through Resolver or Encoder. However, the presence of these sensor elements increases the cost, in addition to reducing the system’s reliability. Moreover, in high wind power turbine, the measured wind speed by the anemometer is taken at the level of the blades which makes the measurement of the wind speed at a single point inaccurate. This paper is a study on the sensorless control that removes the rotor position, speed sensors and anemometer from the speed control. The estimation of the rotor position is based on the output of a rotor current controller and the wind speed estimator is based on the opposition-based learning (OBL), particle swarm optimization and support vector regression.

Neural-Network-Based Adaptive Resilient Dynamic Surface Control Against Unknown Deception Attacks of Uncertain Nonlinear Time-Delay Cyberphysical Systems

A neural-network-based dynamic surface design strategy against sensor and actuator deception attacks is presented to design a delay-independent adaptive resilient control scheme of uncertain nonlinear time-delay cyberphysical systems in the lower triangular form. It is assumed that all nonlinearities, time-varying delays, and sensor and actuator attacks are unknown. In the concerned problem, since the state information measured by sensors is compromised by additional attack signals, the exact state variables are not available for feedback. Thus, a memoryless adaptive resilient control design using compromised state variables is developed by employing the neural-network-based function approximation technique and designing the attack compensator. The resulting control scheme ensures the robust stabilization in the presence of unknown deception attacks and time-varying delays. It is shown from the Lyapunov stability analysis that all closed-loop signals are uniformly ultimately bounded and the stabilization errors converge to an adjustable neighborhood of the origin.

Quantized-Feedback-Based Adaptive Event-Triggered Control of a Class of Uncertain Nonlinear Systems

A quantized-feedback-based adaptive event-triggered tracking problem is investigated for strict-feedback nonlinear systems with unknown nonlinearities and external disturbances. All state variables are quantized through a uniform quantizer and the quantized states are only measurable for the control design. An approximation-based adaptive event-triggered control strategy using quantized states is presented. Compared with the existing recursive quantized feedback control results, the primary contributions of the proposed strategy are (1) to derive a quantized-states-based function approximation mechanism for compensating for unknown and unmatched nonlinearities and (2) to design a quantized-states-based event triggering law for the intermittent update of the control signal. A Lyapunov-based stability analysis is provided to conclude that closed-loop signals are uniformly ultimately bounded and there exists a minimum inter-event time for excluding Zeno behavior. In simulation results, it is shown that the proposed quantized-feedback-based event-triggered control law can be implemented with less than 10% of the total sample data of the existing quantized-feedback continuous control law.

The Effect of Multi-Additional Sampling for Multi-Fidelity Efficient Global Optimization

Powerful computer-aided design tools are presently vital for engineering product development. Efficient global optimization (EGO) is one of the most popular methods for design of a high computational cost problem. The original EGO is proposed for only one additional sample point. In this work, parallel computing is applied to the original EGO process via a multi-additional sampling technique. The weak point of the multi-additional sampling is it has slower convergence rate when compared with the original EGO. This paper applies the multi-fidelity technique to the multi-additional EGO process to see the effect of the number of multi-additional sampling points and the converge rate. A co-kriging method and a hybrid RBF/Kriging surrogate model are selected for the surrogate model in the EGO process to show the advantage of the multi-additional EGO process compared with the single-fidelity Kriging surrogate model. In the experiment, single-additional sampling points and two to four number of multi-additional sampling per iteration are tested with symmetry and asymmetry mathematical test functions. The results show the hybrid RBF/Kriging surrogate model can obtain the similar optimal points when using the multi-additional sampling EGO.

Binless Kernel Machine: Modeling Spike Train Transformation for Cognitive Neural Prostheses

Modeling spike train transformation among brain regions helps in designing a cognitive neural prosthesis that restores lost cognitive functions. Various methods analyze the nonlinear dynamic spike train transformation between two cortical areas with low computational eficiency. The application of a real-time neural prosthesis requires computational eficiency, performance stability, and better interpretation of the neural firing patterns that modulate target spike generation. We propose the binless kernel machine in the point-process framework to describe nonlinear dynamic spike train transformations. Our approach embeds the binless kernel to eficiently capture the feedforward dynamics of spike trains and maps the input spike timings into reproducing kernel Hilbert space (RKHS). An inhomogeneous Bernoulli process is designed to combine with a kernel logistic regression that operates on the binless kernel to generate an output spike train as a point process. Weights of the proposed model are estimated by maximizing the log likelihood of output spike trains in RKHS, which allows a global-optimal solution. To reduce computational complexity, we design a streaming-based clustering algorithm to extract typical and important spike train features. The cluster centers and their weights enable the visualization of the important input spike train patterns that motivate or inhibit output neuron firing. We test the proposed model on both synthetic data and real spike train data recorded from the dorsal premotor cortex and the primary motor cortex of a monkey performing a center-out task. Performances are evaluated by discrete-time rescaling Kolmogorov-Smirnov tests. Our model outperforms the existing methods with higher stability regardless of weight initialization and demonstrates higher eficiency in analyzing neural patterns from spike timing with less historical input (50%). Meanwhile, the typical spike train patterns selected according to weights are validated to encode output spike from the spike train of single-input neuron and the interaction of two input neurons.

Back to the Future: Radial Basis Function Network Revisited

Radial Basis Function (RBF) networks are a classical family of algorithms for supervised learning. The most popular approach for training RBF networks has relied on kernel methods using regularization based on a norm in a Reproducing Kernel Hilbert Space (RKHS), which is a principled and empirically successful framework. In this paper we aim to revisit some of the older approaches to training the RBF networks from a more modern perspective. Specifically, we analyze two common regularization procedures, one based on the square norm of the coefficients in the network and another one using centers obtained by k-means clustering. We show that both of these RBF methods can be recast as certain data-dependent kernels. We provide a theoretical analysis of these methods as well as a number of experimental results, pointing out very competitive experimental performance as well as certain advantages over the standard kernel methods in terms of both flexibility (incorporating of unlabeled data) and computational complexity. Finally, our results shed light on some impressive recent successes of using soft k-means features for image recognition and other tasks.

Monte Carlo Simulations of Au38(SCH3)24 Nanocluster Using Distance-Based Machine Learning Methods

We present an implementation of distance-based machine learning (ML) methods to create a realistic atomistic interaction potential to be used in Monte Carlo simulations of thermal dynamics of thiolate (SR) protected gold nanoclusters. The ML potential is trained for Au₃₈(SR)₂₄ by using previously published, density functional theory (DFT) based, molecular dynamics (MD) simulation data on two experimentally characterized structural isomers of the cluster and validated against independent DFT MD simulations. This method opens a door to efficient probing of the configuration space for further investigations of thermal-dependent electronic and optical properties of Au₃₈(SR)₂₄. Our ML implementation strategy allows for generalization and accuracy control of distance-based ML models for complex nanostructures having several chemical elements and interactions of varying strength.

Condition Monitoring of DC-Link Electrolytic Capacitors in PWM Power Converters Using OBL Method

Since the lifespan of an electrolytic capacitor is relatively short compared to other power semiconductor devices, the failure rate accounts for 60% and, thus, it is the most vulnerable component of the power conversion device. Therefore, the accurate measurement of the lifetime of an electrolytic capacitor is very important in ensuring the reliability of the entire system, including the capacitor. In this paper, an online failure detection method for a DC-link electrolytic capacitor in a back-to-back Pulse width Modulation (PWM) converter using the opposition-based learning particle swarm optimization-based Support Vector Regression (OPSO-SVR) technique is proposed. In this method, the capacitance and the DC-link capacitor power have been used in offline mode for SVR training and testing. During the offline mode, the SVR parameters have been optimized with the OPSO algorithm to use online to estimate the real value of the DC-link capacitor. The experimental results prove the superiority of the proposed technique over the SVR.

Robust control of a silicone soft robot using neural networks

This paper deals with the robust controller design problem to regulate the position of a soft robot with elastic behavior, driven by 4 cable actuators. In this work, we first used an artificial neural network to approximate the relation between these actuators and the controlled position of the soft robot, based on which two types of robust controllers (type of integral and sliding mode) are proposed. The effectiveness and the robustness of the proposed controllers have been analyzed both for the constant and the time-varying disturbances. The performances (precision, convergence speed and robustness) of the proposed method have been validated via different experimental tests.

A feature clustering-based adaptive modular neural network for nonlinear system modeling

To improve the performance of nonlinear system modeling, this study proposes a feature clustering-based adaptive modular neural network (FC-AMNN) by simulating information processing mechanism of human brains in the way that different information is processed by different modules in parallel. Firstly, features are clustered using an adaptive feature clustering algorithm, and the number of modules in FC-AMNN is determined by the number of feature clusters automatically. The features in each cluster are then allocated to the corresponding module in FC-AMNN. Then, a self-constructive RBF neural network based on Error Correction algorithm is adopted as the subnetwork to study the allocated features. All modules work in parallel and are finally integrated using a Bayesian method to obtain the output. To demonstrate the effectiveness of the proposed model, FC-AMNN is tested on several UCI benchmark problems as well as a practical problem in wastewater treatment process. The experimental results show that the FC-AMNN can achieve a better generalization performance and an accurate result for nonlinear system modeling compared with other modular neural networks.

SAMPLING OF SURFACES AND LEARNING FUNCTIONS IN HIGH DIMENSIONS

The efficient representation of data in high-dimensional spaces is a key problem in several machine learning tasks. To capture the non-linear structure of the data, we model the data as points living on a smooth surface. We model the surface as the zero level-set of a bandlimited function. We show that this representation allows a non-linear lifting of the surface model, which will map the points to a low-dimensional subspace. This mapping between surfaces and the well-understood subspace model allows us to introduce novel algorithms (a) to recover the surface from few of its samples and (b) to learn a multidimensional bandlimited function from training data. The utility of these algorithms is introduced in practical applications including image denoising.

Sensorless Active and Reactive Control for DFIG Wind Turbines Using Opposition-Based Learning Technique

In this paper, a wind speed sensorless control method for doubly-fed induction generator (DFIG) control in wind energy systems is proposed. This method is based on using opposition-based learning (OBL) in optimizing the parameters of the support vector regression (SVR) algorithm. These parameters are tuned by applying particle swarm optimization (PSO) method. As a general rule, wind speed measurements are usually done using an anemometer. The measured wind speed by the anemometer is taken at the level of the blades. In a high-power wind turbine, the blade diameter is very large which makes the measurement of the wind speed at a single point inaccurate. Moreover, using anemometers also increases the maintenance cost, complexity and the system cost. Therefore, estimating the wind speed in variable speed wind power systems gives a precise amount of wind speed which is then used in the generator control. The proposed method uses the generator characteristics in mapping a relationship between the generated power, rotational speed and wind speed. This process is carried on off-line and the relationship is then used online to deduce the wind speed based on the obtained relationship. Using OBL with PSO-SVR to tune the SVR parameters accelerates the process to get the optimum parameters in different wind speeds.

Prediction of the performance of artificial neural networks in mapping sEMG to finger joint angles via signal pre-investigation techniques

The inputs to the outputs of nonlinear systems can be modeled using machine and deep learning approaches, among which artificial neural networks (ANNs) are a promising option. However, noisy signals affect ANN modeling negatively; hence, it is important to investigate these signals prior to the modeling. Herein, two customized and simple approaches, visual inspection and absolute correlation, are proposed to examine the relationship between the inputs and outputs of a nonlinear system. The system under consideration uses biosignals from surface electromyography as inputs and human finger joint angles as outputs, acquired from eight intact participants performing movements and grasping tasks in dynamic conditions. Furthermore, the results of these approaches are tested using the standard mutual information measure. Hence, the system dimensionality is reduced, and the ANN learning (convergence) is accelerated, where the most informative inputs are selected for the next phase. Subsequently, four ANN types, i.e., feedforward, cascade-forward, radial basis function, and generalized regression ANNs, are used to perform the modeling. Finally, the performance of the ANNs is compared with findings from the signal analysis. Results indicate a high level of consistency among all the aforementioned signal pre-analysis techniques from one side, and they also indicate that these techniques match the ANN performances from the other side. As an example, for a certain movement set, the ANN models resulted in the rotation estimation accuracy of the joints in the following descending order: carpometacarpal, metacarpophalangeal, proximal interphalangeal, and distal interphalangeal. This information has been indicated in the signal pre-analysis step. Therefore, this step is crucial in input–output variable selections prior to machine-/deep-learning-based modeling approaches.

Universal approximation with quadratic deep networks

Recently, deep learning has achieved huge successes in many important applications. In our previous studies, we proposed quadratic/second-order neurons and deep quadratic neural networks. In a quadratic neuron, the inner product of a vector of data and the corresponding weights in a conventional neuron is replaced with a quadratic function. The resultant quadratic neuron enjoys an enhanced expressive capability over the conventional neuron. However, how quadratic neurons improve the expressing capability of a deep quadratic network has not been studied up to now, preferably in relation to that of a conventional neural network. Specifically, we ask four basic questions in this paper: (1) for the one-hidden-layer network structure, is there any function that a quadratic network can approximate much more efficiently than a conventional network? (2) for the same multi-layer network structure, is there any function that can be expressed by a quadratic network but cannot be expressed with conventional neurons in the same structure? (3) Does a quadratic network give a new insight into universal approximation? (4) To approximate the same class of functions with the same error bound, could a quantized quadratic network have a lower number of weights than a quantized conventional network? Our main contributions are the four interconnected theorems shedding light upon these four questions and demonstrating the merits of a quadratic network in terms of expressive efficiency, unique capability, compact architecture and computational capacity respectively.

Application of near-infrared hyperspectral imaging to identify a variety of silage maize seeds and common maize seeds

Common maize seeds and silage maize seeds are similar in appearance and are difficult to identify with the naked eye. Four varieties of common maize seeds and four varieties of silage maize seeds were identified by near-infrared hyperspectral imaging (NIR-HSI) combined with chemometrics. The pixel-wise principal component analysis was used to distinguish the differences among different varieties of maize seeds. The object-wise spectra of each single seed sample were extracted to build classification models. Support vector machine (SVM) and radial basis function neural network (RBFNN) classification models were established using two different classification strategies. First, the maize seeds were directly classified into eight varieties with the prediction accuracy of the SVM model and RBFNN model over 86%. Second, the seeds of silage maize and common maize were firstly classified with the classification accuracy over 88%, then the seeds were classified into four varieties, respectively. The classification accuracy of silage maize seeds was over 98%, and the classification accuracy of common maize seeds was over 97%. The results showed that the varieties of common maize seeds and silage maize seeds could be classified by NIR-HSI combined with chemometrics, which provided an effective means to ensure the purity of maize seeds, especially to isolate common seeds and silage seeds.

Estimation Methods for Viscosity, Flow Rate and Pressure from Pump-Motor Assembly Parameters

Blood pumps have found applications in heart support devices, oxygenators, and dialysis systems, among others. Often, there is no room for sensors, or the sensors are simply unreliable when long-term operation is required. However, control systems rely on those hard-to-measure parameters, such as blood flow rate and pressure difference, thus their estimation takes a central role in the development process of such medical devices. The viscosity of the blood not only influences the estimation of those parameters but is often a parameter that is of great interest to both doctors and engineers. In this work, estimation methods for blood flow rate, pressure difference, and viscosity are presented using Gaussian process regression models. Different water–glycerol mixtures were used to model blood. Data was collected from a custom-built blood pump, designed for intracorporeal oxygenators in an in vitro test circuit. The estimation was performed from motor current and motor speed measurements and its accuracy was measured for: blood flow rate r² = 0.98, root mean squared error (RMSE) = 46 mL^.min⁻¹; pressure difference r² = 0.98, RMSE = 8.7 mmHg; and viscosity r² = 0.98, RMSE = 0.049 mPa^.s. The results suggest that the presented methods can be used to accurately predict blood flow rate, pressure, and viscosity online.

A Review of Fault Diagnosing Methods in Power Transmission Systems

Transient stability is important in power systems. Disturbances like faults need to be segregated to restore transient stability. A comprehensive review of fault diagnosing methods in the power transmission system is presented in this paper. Typically, voltage and current samples are deployed for analysis. Three tasks/topics; fault detection, classification, and location are presented separately to convey a more logical and comprehensive understanding of the concepts. Feature extractions, transformations with dimensionality reduction methods are discussed. Fault classification and location techniques largely use artificial intelligence (AI) and signal processing methods. After the discussion of overall methods and concepts, advancements and future aspects are discussed. Generalized strengths and weaknesses of different AI and machine learning-based algorithms are assessed. A comparison of different fault detection, classification, and location methods is also presented considering features, inputs, complexity, system used and results. This paper may serve as a guideline for the researchers to understand different methods and techniques in this field.