scispace - formally typeset
Search or ask a question

Showing papers in "IEEE Transactions on Industrial Electronics in 2018"


Journal ArticleDOI
TL;DR: A new CNN based on LeNet-5 is proposed for fault diagnosis which can extract the features of the converted 2-D images and eliminate the effect of handcrafted features and has achieved significant improvements.
Abstract: Fault diagnosis is vital in manufacturing system, since early detections on the emerging problem can save invaluable time and cost. With the development of smart manufacturing, the data-driven fault diagnosis becomes a hot topic. However, the traditional data-driven fault diagnosis methods rely on the features extracted by experts. The feature extraction process is an exhausted work and greatly impacts the final result. Deep learning (DL) provides an effective way to extract the features of raw data automatically. Convolutional neural network (CNN) is an effective DL method. In this study, a new CNN based on LeNet-5 is proposed for fault diagnosis. Through a conversion method converting signals into two-dimensional (2-D) images, the proposed method can extract the features of the converted 2-D images and eliminate the effect of handcrafted features. The proposed method which is tested on three famous datasets, including motor bearing dataset, self-priming centrifugal pump dataset, and axial piston hydraulic pump dataset, has achieved prediction accuracy of 99.79%, 99.481%, and 100%, respectively. The results have been compared with other DL and traditional methods, including adaptive deep CNN, sparse filter, deep belief network, and support vector machine. The comparisons show that the proposed CNN-based data-driven fault diagnosis method has achieved significant improvements.

1,240 citations


Journal ArticleDOI
TL;DR: A convolutional neural network is proposed to detect crack patches in each video frame, while the proposed data fusion scheme maintains the spatiotemporal coherence of cracks in videos, and the Naïve Bayes decision making discards false positives effectively.
Abstract: Regular inspection of nuclear power plant components is important to guarantee safe operations. However, current practice is time consuming, tedious, and subjective, which involves human technicians reviewing the inspection videos and identifying cracks on reactors. A few vision-based crack detection approaches have been developed for metallic surfaces, and they typically perform poorly when used for analyzing nuclear inspection videos. Detecting these cracks is a challenging task since they are tiny, and noisy patterns exist on the components’ surfaces. This study proposes a deep learning framework, based on a convolutional neural network (CNN) and a Naive Bayes data fusion scheme, called NB-CNN, to analyze individual video frames for crack detection while a novel data fusion scheme is proposed to aggregate the information extracted from each video frame to enhance the overall performance and robustness of the system. To this end, a CNN is proposed to detect crack patches in each video frame, while the proposed data fusion scheme maintains the spatiotemporal coherence of cracks in videos, and the Naive Bayes decision making discards false positives effectively. The proposed framework achieves a 98.3% hit rate against 0.1 false positives per frame that is significantly higher than state-of-the-art approaches as presented in this paper.

649 citations


Journal ArticleDOI
TL;DR: Inspired by the success of deep learning methods that redefine representation learning from raw data, this work proposes local feature-based gated recurrent unit (LFGRU) networks, a hybrid approach that combines handcrafted feature design with automatic feature learning for machine health monitoring.
Abstract: In modern industries, machine health monitoring systems (MHMS) have been applied wildly with the goal of realizing predictive maintenance including failures tracking, downtime reduction, and assets preservation. In the era of big machinery data, data-driven MHMS have achieved remarkable results in the detection of faults after the occurrence of certain failures (diagnosis) and prediction of the future working conditions and the remaining useful life (prognosis). The numerical representation for raw sensory data is the key stone for various successful MHMS. Conventional methods are the labor-extensive as they usually depend on handcrafted features, which require expert knowledge. Inspired by the success of deep learning methods that redefine representation learning from raw data, we propose local feature-based gated recurrent unit (LFGRU) networks. It is a hybrid approach that combines handcrafted feature design with automatic feature learning for machine health monitoring. First, features from windows of input time series are extracted. Then, an enhanced bidirectional GRU network is designed and applied on the generated sequence of local features to learn the representation. A supervised learning layer is finally trained to predict machine condition. Experiments on three machine health monitoring tasks: tool wear prediction, gearbox fault diagnosis, and incipient bearing fault detection verify the effectiveness and generalization of the proposed LFGRU.

558 citations


Journal ArticleDOI
TL;DR: A new method to perform accurate SOC estimation for Li-ion batteries using a recurrent neural network (RNN) with long short-term memory (LSTM) to showcase the LSTM-RNN's ability to encode dependencies in time and accurately estimate SOC without using any battery models, filters, or inference systems like Kalman filters.
Abstract: State of charge (SOC) estimation is critical to the safe and reliable operation of Li-ion battery packs, which nowadays are becoming increasingly used in electric vehicles (EVs), Hybrid EVs, unmanned aerial vehicles, and smart grid systems. We introduce a new method to perform accurate SOC estimation for Li-ion batteries using a recurrent neural network (RNN) with long short-term memory (LSTM). We showcase the LSTM-RNN's ability to encode dependencies in time and accurately estimate SOC without using any battery models, filters, or inference systems like Kalman filters. In addition, this machine-learning technique, like all others, is capable of generalizing the abstractions it learns during training to other datasets taken under different conditions. Therefore, we exploit this feature by training an LSTM-RNN model over datasets recorded at various ambient temperatures, leading to a single network that can properly estimate SOC at different ambient temperature conditions. The LSTM-RNN achieves a low mean absolute error (MAE) of 0.573% at a fixed ambient temperature and an MAE of 1.606% on a dataset with ambient temperature increasing from 10 to 25 $^{\circ }$ C.

436 citations


Journal ArticleDOI
TL;DR: A novel support vector regression-based battery SOH state-space model is established to simulate the battery aging mechanism and the results show that the proposed SOH estimation method can provide an accurate and robustness result.
Abstract: Accurate remaining useful life (RUL) prediction and state-of-health (SOH) diagnosis are of extreme importance for safety, durability, and cost of energy storage systems based on lithium-ion batteries. It is also a crucial challenge for energy storage systems to predict RUL and diagnose SOH of batteries due to the complicated aging mechanism. In this paper, a novel method for battery RUL prediction and SOH estimation is proposed. First, a novel support vector regression-based battery SOH state-space model is established to simulate the battery aging mechanism, which takes the capacity as the state variable and takes the representative features during a constant-current and constant-voltage protocol as the input variables. The estimated impedance variables are taken as the output due to the correlation between battery capacity and the sum of charge transfer resistance and electrolyte resistance. Second, in order to suppress the measurement noises of current and voltage, a particle filter is employed to estimate the impedance degradation parameters. Furthermore, experiments are conducted to validate the proposed method. The results show that the proposed SOH estimation method can provide an accurate and robustness result. The proposed RUL prediction framework can also ensure an accurate RUL prediction result.

364 citations


Journal ArticleDOI
TL;DR: A novel convolutional deep belief network (CDBN) is proposed for bearing fault diagnosis with an auto-encoder used to compress data and reduce the dimension and exponential moving average is employed to improve the performance of the constructed deep model.
Abstract: Bearing fault diagnosis is of significance to enhance the reliability and security of electric locomotive. In this paper, a novel convolutional deep belief network (CDBN) is proposed for bearing fault diagnosis. First, an auto-encoder is used to compress data and reduce the dimension. Second, a novel CDBN is constructed with Gaussian visible units to learn the representative features. Third, exponential moving average is employed to improve the performance of the constructed deep model. The proposed method is applied to analyze experimental signals collected from electric locomotive bearings. The results show that the proposed method is more effective than the traditional methods and standard deep learning methods.

336 citations


Journal ArticleDOI
TL;DR: A robot control/identification scheme to identify the unknown robot kinematic and dynamic parameters with enhanced convergence rate was developed, and the information of parameter estimation error was properly integrated into the proposed identification algorithm, such that enhanced estimation performance was achieved.
Abstract: For parameter identifications of robot systems, most existing works have focused on the estimation veracity, but few works of literature are concerned with the convergence speed. In this paper, we developed a robot control/identification scheme to identify the unknown robot kinematic and dynamic parameters with enhanced convergence rate. Superior to the traditional methods, the information of parameter estimation error was properly integrated into the proposed identification algorithm, such that enhanced estimation performance was achieved. Besides, the Newton–Euler (NE) method was used to build the robot dynamic model, where a singular value decomposition-based model reduction method was designed to remedy the potential singularity problems of the NE regressor. Moreover, an interval excitation condition was employed to relax the requirement of persistent excitation condition for the kinematic estimation. By using the Lyapunov synthesis, explicit analysis of the convergence rate of the tracking errors and the estimated parameters were performed. Simulation studies were conducted to show the accurate and fast convergence of the proposed finite-time (FT) identification algorithm based on a 7-DOF arm of Baxter robot.

321 citations


Journal ArticleDOI
TL;DR: A novel Lyapunov-based model predictive control (LMPC) framework is developed for the AUV to utilize computational resource (online optimization) to improve the trajectory tracking performance.
Abstract: This paper studies the trajectory tracking control problem of an autonomous underwater vehicle (AUV). We develop a novel Lyapunov-based model predictive control (LMPC) framework for the AUV to utilize computational resource (online optimization) to improve the trajectory tracking performance. Within the LMPC framework, the practical constraints, such as actuator saturation, can be explicitly considered. Also, the thrust allocation subproblem can be addressed simultaneously with the LMPC controller design. Taking advantage of a nonlinear backstepping tracking control law, we construct the contraction constraint in the formulated LMPC problem so that the closed-loop stability is theoretically guaranteed. Sufficient conditions that ensure the recursive feasibility, and hence the closed-loop stability, are provided analytically. A guaranteed region of attraction is explicitly characterized. In the meantime, the robustness of the tracking control can be improved by the receding horizon implementation that is adopted in the LMPC control algorithm. Simulation results on the Saab SeaEye Falcon model AUV demonstrate the significantly enhance trajectory tracking control performance via the proposed LMPC method.

303 citations


Journal ArticleDOI
TL;DR: A variant of deep residual networks (DRNs) with dynamically weighted wavelet coefficients (DRN+DWWC) to improve diagnostic performance, which takes a series of sets of wavelet packet coefficients on various frequency bands as an input.
Abstract: One of the significant tasks in data-driven fault diagnosis methods is to configure a good feature set involving statistical parameters. However, statistical parameters are often incapable of representing the dynamic behavior of planetary gearboxes under variable operating conditions. Although the use of deep learning algorithms to find a good set of features for fault diagnosis has somewhat improved diagnostic performance, the lack of domain knowledge incorporated into deep learning algorithms has limited further improvement. Accordingly, this paper developed a variant of deep residual networks (DRNs), the so-called deep residual networks with dynamically weighted wavelet coefficients (DRN+DWWC) to improve diagnostic performance, which takes a series of sets of wavelet packet coefficients on various frequency bands as an input. Further, the fact that no general consensus has been reached as to which frequency band contains the most intrinsic information about a planetary gearbox's health status calls for “dynamic weighting layers” in the DRN+DWWC and the role of the layers is to dynamically adjust a weight applied to each set of wavelet packet coefficients to find a discriminative set of features that will be further used for planetary gearbox fault diagnosis.

281 citations


Journal ArticleDOI
TL;DR: An adaptive event- triggering LFC scheme is presented, where the event-triggering threshold can be dynamically adjusted to save more limited network resources, while preserving the desired control performance.
Abstract: Load frequency control (LFC) is a very important method to keep the power systems stable and secure. However, due to the introduction of communication networks in multi-area power systems, the traditional LFC method is not effective again. This motivates us to investigate an adaptive event-triggering ${H}_{\infty }$ LFC scheme for multi-area power systems. Compared with the existing time-invariant event-triggering communication scheme, an adaptive event-triggering communication scheme is presented, where the event-triggering threshold can be dynamically adjusted to save more limited network resources, while preserving the desired control performance. Compared with the existing emulation-based method, where the controller must be known a priori , the stability and stabilization criteria derived in this work can provide a tradeoff to balance the required communication resources and the desired control performance. The effectiveness of the proposed method is verified by two numerical examples.

276 citations


Journal ArticleDOI
TL;DR: A novel transformerless high gain step-up dc–dc converter based on an active switched-inductor and a passive switched-capacitor networks that has the main advantages of the high voltage gain (>10), the reduced voltage stresses across the switches and the reduced number of components when compared to topologies that provide the same voltage gain using similar principles.
Abstract: High-gain voltage conversion is a feature required for several applications, especially for power processing of low-voltage renewable sources in grid-connected systems. In this scope, the presented paper proposes a novel transformerless high gain step-up dc–dc converter based on an active switched-inductor and a passive switched-capacitor networks. The main advantages of the proposed converter are the high voltage gain (>10), the reduced voltage stresses across the switches and the reduced number of components when compared to topologies that provide the same voltage gain using similar principles. The detailed analysis of the proposed converter and a comparison considering other topologies previously published in the literature are also presented in this manuscript. In order to verify the proposed converter performance, a prototype has been built for a power of 200 W, input and output voltages of 20 and 260 V, respectively, and switching frequency of 50 kHz. Experimental results validate the effectiveness of the theoretical analysis proving the satisfactory converter performance, which peak efficiency is around 95.5%.

Journal ArticleDOI
TL;DR: An FD technique combining the generalized CCA with the threshold-setting based on the randomized algorithm is proposed and applied to the simulated traction drive control system of high-speed trains and shows that the proposed method is able to improve the detection performance significantly in comparison with the standard generalized C CA-based FD method.
Abstract: In this paper, we first study a generalized canonical correlation analysis (CCA)-based fault detection (FD) method aiming at maximizing the fault detectability under an acceptable false alarm rate. More specifically, two residual signals are generated for detecting of faults in input and output subspaces, respectively. The minimum covariances of the two residual signals are achieved by taking the correlation between input and output into account. Considering the limited application scope of the generalized CCA due to the Gaussian assumption on the process noises, an FD technique combining the generalized CCA with the threshold-setting based on the randomized algorithm is proposed and applied to the simulated traction drive control system of high-speed trains. The achieved results show that the proposed method is able to improve the detection performance significantly in comparison with the standard generalized CCA-based FD method.

Journal ArticleDOI
TL;DR: A family of novel flying capacitor transformerless inverters for single-phase photovoltaic (PV) systems based on a flying capacitor principle and requires only four power switches and/or diodes, one capacitor, and a small filter at the output stage is proposed.
Abstract: This paper proposes a family of novel flying capacitor transformerless inverters for single-phase photovoltaic (PV) systems. Each of the new topologies proposed is based on a flying capacitor principle and requires only four power switches and/or diodes, one capacitor, and a small filter at the output stage. A simple unipolar sinusoidal pulse width modulation technique is used to modulate the inverter to minimize the switching loss, output current ripple, and the filter requirements. In general, the main advantages of the new inverter topologies are: 1) the negative polarity of the PV is directly connected to the grid, and therefore, no leakage current; 2) reactive power compensation capability; and 3) the output ac voltage peak is equal to the input dc voltage (unlike neutral-point-clamped and derivative topologies, which requires twice the magnitude of the peak ac voltage). A complete description of the operating principle with modulation techniques, design guidelines, and comprehensive comparisons is presented to reveal the properties and limitations of each topology in detail. Finally, experimental results of 1-kVA prototypes are presented to prove the concept and theoretical analysis of the proposed inverter family for practical applications.

Journal ArticleDOI
TL;DR: Comparison results indicate that IMMTP could achieve a more accurate prediction trajectory with a long prediction horizon than the existing physics- and maneuver-based approaches.
Abstract: Vehicle trajectory prediction helps automated vehicles and advanced driver-assistance systems have a better understanding of traffic environment and perform tasks such as criticality assessment in advance. In this study, an integrated vehicle trajectory prediction method is proposed by combining physics- and maneuver-based approaches. These two methods were combined for the reason that the physics-based trajectory prediction method could ensure accuracy in the short term with the consideration of vehicle running dynamic parameters, and the maneuver-based prediction approach has a long-term insight into future trajectories with maneuver estimation. In this study, the interactive multiple model trajectory prediction (IMMTP) method is proposed by combining the two predicting models. The probability of each model in the interactive multiple models could recursively adjust according to the predicting variance of each model. In addition, prediction uncertainty is considered by employing unscented Kalman filters in the physics-based prediction model. To the maneuver-based method, random elements for uncertainty are introduced to the trajectory of each maneuver inferred by using the dynamic Bayesian network. The approach is applied and analyzed in the lane-changing scenario by using naturalistic driving data. Comparison results indicate that IMMTP could achieve a more accurate prediction trajectory with a long prediction horizon.

Journal ArticleDOI
TL;DR: An adaptive formation control that ensures internal stability of closed-loop systems with guaranteed prescribed performance is proposed and both collision avoidance and connectivity maintenance between two consecutive vehicles are guaranteed during the whole operation.
Abstract: This paper studies the platoon formation control problem for unmanned surface vehicles, in the presence of modeling uncertainties and time-varying external disturbances. The control objective is to make the vehicular platoons proceed along a given trajectory while maintaining a desired line-of-sight (LOS) range between each vehicle and its predecessor. To provide transient performance specifications on formation errors, including LOS range and angle errors, we enforce prescribed performance guarantees in the control design. The prescribed performance guarantees mean that formation errors evolve always within the predefined regions that are bounded by exponentially decaying functions of time. Using prescribed performance control methodology, neural network approximation, disturbance observers, dynamic surface control technique, and Lyapunov synthesis, we propose an adaptive formation control that ensures internal stability of closed-loop systems with guaranteed prescribed performance. Meanwhile, both collision avoidance and connectivity maintenance between two consecutive vehicles are guaranteed during the whole operation. The proposed formation control is decentralized in the sense that the control action on each vehicle depends only on information from its immediate predecessor. Simulation results demonstrate the performance of the proposed control.

Journal ArticleDOI
TL;DR: A discontinuous Lyapunov functional approach is developed to derive a design criterion on the existence of an admissible sampled-data CFP for cluster formation control for a networked multi-agent system in the simultaneous presence of aperiodic sampling and communication delays.
Abstract: This paper addresses the problem of cluster formation control for a networked multi-agent system (MAS) in the simultaneous presence of aperiodic sampling and communication delays. First, to fulfill multiple formation tasks, a group of agents are decomposed into $M$ distinct and nonoverlapping clusters. The agents in each cluster are then driven to achieve a desired formation, whereas the MAS as a whole accomplishes $ M $ cluster formations. Second, by a proper modeling of aperiodic sampling and communication delays, an aperiodic sampled-data cluster formation protocol (CFP) is delicately constructed such that the information exchanges among neighboring agents only occur intermittently at discrete instants of time. Third, a detailed theoretical analysis of cluster formability is carried out and a sufficient and necessary condition is provided such that the system is $M$ -cluster formable. Furthermore, a discontinuous Lyapunov functional approach is developed to derive a design criterion on the existence of an admissible sampled-data CFP. Finally, numerical simulations on a team of nonholonomic mobile robots are given to illustrate the effectiveness of the obtained theoretical result.

Journal ArticleDOI
Le Yao1, Zhiqiang Ge1
TL;DR: The proposed semisupervised HELM method is applied in a high–low transformer to estimate the carbon monoxide content, which shows a significant improvement of the prediction accuracy, compared to traditional methods.
Abstract: Data-driven soft sensors have been widely utilized in industrial processes to estimate the critical quality variables which are intractable to directly measure online through physical devices. Due to the low sampling rate of quality variables, most of the soft sensors are developed on small number of labeled samples and the large number of unlabeled process data is discarded. The loss of information greatly limits the improvement of quality prediction accuracy. One of the main issues of data-driven soft sensor is to furthest exploit the information contained in all available process data. This paper proposes a semisupervised deep learning model for soft sensor development based on the hierarchical extreme learning machine (HELM). First, the deep network structure of autoencoders is implemented for unsupervised feature extraction with all the process samples. Then, extreme learning machine is utilized for regression through appending the quality variable. Meanwhile, the manifold regularization method is introduced for semisupervised model training. The new method can not only deeply extract the information that the data contains, but learn more from the extra unlabeled samples as well. The proposed semisupervised HELM method is applied in a high–low transformer to estimate the carbon monoxide content, which shows a significant improvement of the prediction accuracy, compared to traditional methods.

Journal ArticleDOI
TL;DR: An innovative method employing the weighted Gaussian process regression approach is proposed, such that data samples with higher outlier potential have a low weight, and the results exhibit higher estimation accuracy.
Abstract: Photovoltaic (PV) power is volatile in nature and raises the level of uncertainty in power systems. PV power forecasting is an important measure to solve this problem. It helps to improve the reliability and reduces the generation cost. Advances in computer technology and sensors make the numeric modeling methods a hotspot in the field of PV power forecasting. However, data modeling methods strongly rely on the accuracy of measurement data. Unavoidable outliers in the measured meteorological data have an adverse effect on the model due to their heteroscedasticity. Although many studies can be found focusing on outlier detection, only a few have incorporated outlier detection with regression models. In this study, an innovative method employing the weighted Gaussian process regression approach is proposed, such that data samples with higher outlier potential have a low weight. A density-based local outlier detection approach is introduced to compensate the deterioration of Euclidean distance for high-dimensional data. A novel concept of the degree of nonlinear correlation is incorporated to compute the contribution of every individual data attribute. Effectiveness of the proposed method is demonstrated by performing an experimental analysis and making comparisons with other typical data-based approaches, and the results exhibit higher estimation accuracy.

Journal ArticleDOI
TL;DR: Results indicate that the proposed control enables the human subjects to execute an admittance control task on the exoskeleton robot effectively and the robustness of the variable stiffness control is guaranteed.
Abstract: In this paper, a physical human–robot interaction approach is presented for the developed robotic exoskeleton using admittance control to deal with a human subject's intention as well as the unknown inertia masses and moments in the robotic dynamics. The human subject's intention is represented by the reference trajectory when the robotic exoskeleton is complying with the external interaction force. Online estimation of the stiffness is employed to deal with the variable impedance property of the robotic exoskeleton. Admittance control is first presented based on the measured force in order to generate a reference trajectory in interaction tasks. Then, adaptive control is proposed to deal with the uncertain robotic dynamics and a stability criterion can be obtained. Bounded errors are shown in the motion tracking while the robustness of the variable stiffness control is guaranteed. The experimental results indicate that the proposed control enables the human subjects to execute an admittance control task on the exoskeleton robot effectively.

Journal ArticleDOI
Jun Pan1, Yanyang Zi1, Jinglong Chen1, Zitong Zhou1, Biao Wang 
TL;DR: Results show that the proposed method could achieve layerwise feature learning and successfully classify mechanical data even with different rotating speed and under the influence of random noise.
Abstract: The key challenge of intelligent fault diagnosis is to develop features that can distinguish different categories. Because of the unique properties of mechanical data, predetermined features based on prior knowledge are usually used as inputs for fault classification. However, proper selection of features often requires expertise knowledge and becomes more difficult and time consuming when volume of data increases. In this paper, a novel deep learning network (LiftingNet) is proposed to learn features adaptively from raw mechanical data without prior knowledge. Inspired by convolutional neural network and second generation wavelet transform, the LiftingNet is constructed to classify mechanical data even though inputs contain considerable noise and randomness. The LiftingNet consists of split layer, predict layer, update layer, pooling layer, and full-connection layer. Different kernel sizes are allowed in convolutional layers to improve learning ability. As a multilayer neural network, deep features are learned from shallow ones to represent complex structures in raw data. Feasibility and effectiveness of the LiftingNet is validated by two motor bearing datasets. Results show that the proposed method could achieve layerwise feature learning and successfully classify mechanical data even with different rotating speed and under the influence of random noise.

Journal ArticleDOI
TL;DR: A multivariable super-twisting-like algorithm (STLA) is proposed for arbitrary order integrator systems subject to matched disturbances and a discontinuous integral term is incorporated in the control law in order to compensate the disturbances.
Abstract: The attitude control of quadrotor unmanned aerial vehicle (UAV) is investigated. The aim of this paper is to develop a continuous multivariable attitude control law, which drives the attitude tracking errors of quadrotor UAV to zero in finite time. First, a multivariable super-twisting-like algorithm (STLA) is proposed for arbitrary order integrator systems subject to matched disturbances. A discontinuous integral term is incorporated in the control law in order to compensate the disturbances. A rigorous proof of the finite time stability of the close-loop system is derived by utilizing the Lyapunov method and the homogeneous technique. Then, the implementation of the developed method in an indoor quadrotor UAV is performed. The remarkable features of the developed algorithm includes the finite time convergence, the chattering suppression and the nominal performance recovery. Finally, the efficiency of the proposed method is illustrated by numerical simulations and experimental verification.

Journal ArticleDOI
TL;DR: Two finite-set model-predictive control methodologies for a grid-connected three-level neutral-point-clamped converter are investigated and show a good performance, in steady-state and transient response, with a total harmonic distortion lower than $\text{2}\%$ for the currents supplied to the grid.
Abstract: In this paper, finite-set model-predictive control (FS-MPC) methodologies for a grid-connected three-level neutral-point-clamped converter are investigated. The proposed control strategies produce fixed switching frequency, maintaining all the advantages of predictive control such as fast dynamic response, inclusion of nonlinearities and restrictions, and multivariable control using a single control loop. The first of the proposed FS-MPC strategies is based on a multiobjective cost function, designed to regulate both the inverter currents and the balancing of the dc-link capacitor voltages. The second FS-MPC strategy is derived from the first one, and it is based on a cost function that regulates only the grid current, with the balancing of the capacitor voltages being realized by controlling the duty cycles of the redundant vectors. The proposed control systems are experimentally validated using a 5-kW prototype. The experimental results show a good performance for both strategies, in steady-state and transient response, with a total harmonic distortion lower than $\text{2}\%$ for the currents supplied to the grid.

Journal ArticleDOI
TL;DR: This work suggests the integration of virtual voltage vectors (VVs) into the FCS-MPC structure, confirming that the VV-based MPC maintains the flux/torque regulation and successfully improves the power quality and efficiency.
Abstract: The most serious and recent competitor to the standard field oriented control for induction motors (IM) is the finite control set model predictive control (FCS-MPC). Nevertheless, the extension to multiphase drives faces the impossibility to simultaneously regulate the flux/torque and the secondary current components (typically termed $x - y$ in the literature). The application of a single switching state during the whole sampling period inevitably implies the appearance of $x - y$ voltage/currents that increase the system losses and deteriorate the power quality. These circulating currents become intolerably high as per the unit $x - y$ impedance and the switching frequency diminish. Aiming to overcome this limitation, this work suggests the integration of virtual voltage vectors (VVs) into the FCS-MPC structure. The VVs ensure null $x - y$ voltages on average during the sampling period and the MPC approach selects the most suitable VV to fulfill the flux/torque requirements. The experimental results for a six-phase case study compare the standard FCS-MPC with the suggested method, confirming that the VV-based MPC maintains the flux/torque regulation and successfully improves the power quality and efficiency.

Journal ArticleDOI
TL;DR: The finite-time multivariable terminal sliding mode control and composite-loop design are pursued to enable integration into the FTC, which can ensure the safety of the postfault vehicle in a timely manner.
Abstract: This paper proposes a fault-tolerant control (FTC) scheme for a hypersonic gliding vehicle to counteract actuator faults and model uncertainties. Starting from the kinematic and aerodynamic models of the hypersonic vehicle, the control-oriented model subject to actuator faults is built. The observers are designed to estimate the information of actuator faults and model uncertainties, and to guarantee the estimation errors for converging to zero in fixed settling time. Subsequently, the finite-time multivariable terminal sliding mode control and composite-loop design are pursued to enable integration into the FTC, which can ensure the safety of the postfault vehicle in a timely manner. Simulation studies of a six degree-of-freedom nonlinear model of the hypersonic gliding vehicle are carried out to manifest the effectiveness of the investigated FTC system.

Journal ArticleDOI
TL;DR: Rigorous analysis is provided to demonstrate that the fast terminal SMC law can offer a higher accuracy than the traditional linear SMClaw and show the advantages of the present discrete-time fast terminalSMC approach over some existing approaches, such as discrete- time linear sliding mode control approach and the PID control method.
Abstract: The main objective of this paper is to solve the position tracking control problem for the permanent magnet linear motor by using the discrete-time fast terminal sliding mode control (SMC) method. Specifically, based on Euler's discretization technique, the approximate discrete-time model is first obtained and analyzed. Then, by introducing a new type of discrete-time fast terminal sliding surface, an improved discrete-time fast SMC method is developed and an equivalent-control-based fast terminal SMC law is subsequently designed. Rigorous analysis is provided to demonstrate that the fast terminal SMC law can offer a higher accuracy than the traditional linear SMC law. Numerical simulations and experimental results are finally performed to demonstrate the effectiveness of the proposed approach and show the advantages of the present discrete-time fast terminal SMC approach over some existing approaches, such as discrete-time linear sliding mode control approach and the PID control method.

Journal ArticleDOI
TL;DR: An energy storage (ES)-equipped energy-sharing provider (ESP) is proposed to facilitate the energy sharing of multiple PV prosumers and the effectiveness of the method is verified in terms of improving the economic benefits and PV energy sharing.
Abstract: According to the energy policy, which encourages local consumption of photovoltaic (PV) energy, the energy sharing among neighboring PV prosumers is proved to be a more effective way compared with independent operations of each prosumer. In this paper, an energy storage (ES)-equipped energy-sharing provider (ESP) is proposed to facilitate the energy sharing of multiple PV prosumers. With the help of the ESP, the autonomous PV prosumers can be formed as an energy-sharing network, and the energy-sharing activities can be categorized as direct sharing and buffered sharing. First, with the assistance of the ES, a day-ahead scheduling model of the ESP is built to increase the operation profit and improve the net power profile of the energy-sharing network, which considers the uncertainty of PV energy, electricity prices, and prosumers’ load via stochastic programming. Moreover, to further increase the energy sharing, a real-time demand response model based on a Stackelberg game is presented to coordinate the energy consumption behavior of prosumers by using internal prices. Finally, through a practical case study, the effectiveness of the method is verified in terms of improving the economic benefits and PV energy sharing.

Journal ArticleDOI
TL;DR: This paper proposes a novel, fast, and accurate water leakage detection system with an adaptive design that fuses a one-dimensional convolutional neural network and a support vector machine and proposes a graph-based localization algorithm to determine the leakage location.
Abstract: In many water distribution systems, a significant amount of water is lost because of leakage during transit from the water treatment plant to consumers. As a result, water leakage detection and localization have been a consistent focus of research. Typically, diagnosis or detection systems based on sensor signals incur significant computational and time costs, whereas the system performance depends on the features selected as input to the classifier. In this paper, to solve this problem, we propose a novel, fast, and accurate water leakage detection system with an adaptive design that fuses a one-dimensional convolutional neural network and a support vector machine. We also propose a graph-based localization algorithm to determine the leakage location. An actual water pipeline network is represented by a graph network and it is assumed that leakage events occur at virtual points on the graph. The leakage location at which costs are minimized is estimated by comparing the actual measured signals with the virtually generated signals. The performance was validated on a wireless sensor network based test bed, deployed on an actual WDS. Our proposed methods achieved 99.3% leakage detection accuracy and a localization error of less than 3 m.

Journal ArticleDOI
TL;DR: This paper implements battery remaining available energy prediction and state-of-charge (SOC) estimation against testing temperature uncertainties, as well as inaccurate initial SOC values, against a double-scale particle filtering method.
Abstract: In order for the battery management system (BMS) in an electric vehicle to function properly, accurate and robust indication of the energy state of the lithium-ion batteries is necessary. This robustness requires that the energy state can be estimated accurately even when the working conditions of batteries change dramatically. This paper implements battery remaining available energy prediction and state-of-charge (SOC) estimation against testing temperature uncertainties, as well as inaccurate initial SOC values. A double-scale particle filtering method has been developed to estimate or predict the system state and parameters on two different time scales. The developed method considers the slow time-varying characteristics of the battery parameter set and the quick time-varying characteristics of the battery state set. In order to select the preferred battery model, the Akaike information criterion (AIC) is used to make a tradeoff between the model prediction accuracy and complexity. To validate the developed double-scale particle filtering method, two different kinds of lithium-ion batteries were tested at three temperatures. The experimental results show that, with 20% initial SOC deviation, the maximum remaining available energy prediction and SOC estimation errors are both within 2%, even when the wrong temperature is indicated. In this case, the developed double-scale particle filtering method is expected to be robust in practice.

Journal ArticleDOI
TL;DR: The steady-state analysis of the proposed dc–dc converter with high voltage gain is discussed and the proposed converter prototype circuit is implemented to justify the validity of the analysis.
Abstract: In this paper, a nonisolated dc–dc converter with high voltage gain is presented. Three diodes, three capacitors, an inductor, and a coupled inductor are employed in the presented converter. Since the inductor is connected to the input, the low input current ripple is achieved, which is important for tracking maximum power point of photovoltaic panels. The voltage stress across switch S is clamped by diode D 1 and capacitor C 1. Therefore, a main switch with low on-resistance RDS (on) can be employed to reduce the conduction loss. Besides, the main switch is turned on under zero current. This reduces the switching loss. The steady-state analysis of the proposed converter is discussed in this paper. Finally, the proposed converter prototype circuit is implemented to justify the validity of the analysis.

Journal ArticleDOI
TL;DR: A nonisolated high gain dc–dc converter is proposed without using the voltage multiplier cell and/or hybrid switched-capacitor technique to achieve high voltage gain without using extreme duty ratio.
Abstract: DC microgrids are popular due to the integration of renewable energy sources such as solar photovoltaics and fuel cells. Owing to the low output voltage of these dc power generators, high efficient high gain dc–dc converters are in need to connect the dc microgrid. In this paper, a nonisolated high gain dc–dc converter is proposed without using the voltage multiplier cell and/or hybrid switched-capacitor technique. The proposed topology utilizes two nonisolated inductors that are connected in series/parallel during discharging/charging mode. The operation of switches with two different duty ratios is the main advantage of the converter to achieve high voltage gain without using extreme duty ratio. The steady-state analysis of the proposed converter using two different duty ratios is discussed in detail. In addition, a 100 W, 20/200 V prototype circuit of the high gain dc–dc converter is developed, and the performance is validated using experimental results.