Showing papers in "IEEE Transactions on Industrial Electronics in 2022"
TL;DR: The results confirm the feasibility of the proposed modified deep autoencoder driven by multi-source parameters in cross-domain fault prognosis of aeroengines, which outperforms the existing methods.
Abstract: The existing fault prognosis techniques of aeroengine mostly focus on a single monitoring parameter under stable condition, and have low adaptability to new prognosis scenes. To boost the fault prognosis capability cross aeroengines, modified deep autoencoder (MDAE) driven by multi-source parameters is proposed in this article. First, the sensitive multi-source parameters are selected and fused using linear local tangent space alignment to define a fused health index (FHI) to characterize performance degradation of aeroengine. Second, MDAE model is constructed with adaptive Morlet wavelet to flexibly establish accurate mapping hidden in the FHI under analysis. Third, parameter transfer learning is used to provide good initial parameters for enabling the constructed MDAE to have cross-domain fault prognosis capability. The proposed method is used to analyze both the simulation multisource performance degradation parameters of aeroengines (system level) and experiment run-to-failure bearing datasets (component level). The results confirm the feasibility of the proposed method in cross-domain fault prognosis of aeroengines, which outperforms the existing methods.
104 citations
TL;DR: Simulation results show that APSO-GA can easily find feasible solutions particularly when the number of switching angles is high; however, the rest of all stuck at local minima due to less exploration capability.
Abstract: In this article, a hybrid asynchronous particle swarm optimization-genetic algorithm (APSO-GA) is proposed for the removal of unwanted lower order harmonics in the cascaded H-bridge multilevel inverter (MLI). The APSO-GA is applicable to all levels of MLI. In the proposed method, ring topology based APSO is hybrid with GA. APSO is applied for exploration and GA is used for the exploitation of the best solutions. In this article, optimized switching angles are calculated using APSO-GA for seven-level and nine-level inverter, and results are compared with GA, PSO, APSO, bee algorithm (BA), differential evolution (DE), synchronous PSO, and teaching–learning-based optimization (TLBO). Simulation results show that APSO-GA can easily find feasible solutions particularly when the number of switching angles is high; however, the rest of all stuck at local minima due to less exploration capability. Also, the APSO-GA is less computational complex than GA, BA, TLBO, and DE algorithms. Experimentally, the performance of APSO-GA is validated on a single-phase seven-level inverter.
86 citations
TL;DR: A novel ISC diagnostic method leveraging polarization dynamics instead of the conventional charge depletion is proposed within a model-switching framework to mitigate the adverse effect of measurement disturbances and contribute to an unbiased estimation of the ISC resistance.
Abstract: The accurate diagnostic of internal short circuit (ISC) is critical to the safety of lithium-ion battery (LIB), considering its consequence to disastrous thermal runaway. Motivated by this, this article proposes a novel ISC diagnostic method with a high robustness to measurement disturbances and the capacity fading. Particularly, a multistate-fusion ISC diagnostic method leveraging polarization dynamics instead of the conventional charge depletion is proposed within a model-switching framework. This is well-proven to eliminate the vulnerability of diagnostic to battery aging. Within this framework, the recursive total least squares method with variant forgetting is exploited, for the first time, to mitigate the adverse effect of measurement disturbances, which contributes to an unbiased estimation of the ISC resistance. The proposed method is validated both theoretically and experimentally for high diagnostic accuracy as well as the strong robustness to battery degradation and disturbance.
65 citations
TL;DR: A quantitative tuning rule for the time-delayed ADRC (TD-ADRC) structure based on the typical first order plus time delay (FOPTD) model is proposed, revealing Relative delay margin is revealed as a critical robustness metric among others.
Abstract: Active disturbance rejection controller (ADRC) has achieved soaring success in motion controls featured by rapid dynamics. However, it turns obstreperous to implement it in the power plant process with considerable time-delay, largely because of the tuning difficulty. To this end, this article proposes a quantitative tuning rule for the time-delayed ADRC (TD-ADRC) structure based on the typical first order plus time delay (FOPTD) model. By compensating the FOPTD process as an integrator plus time delay in low frequencies, the gain parameter of TD-ADRC can be related to a scaled time constant which shapes the closed-loop tracking performance. Bandwidth parameter of extended state observer is scaled as a dimensionless parameter. A sufficient stability condition of TD-ADRC is theoretically derived in terms of the scaled parameter pair, the range of which falls within the practical interest. Relative delay margin is revealed as a critical robustness metric among others, a default pair of scaled parameter setting is recommended as well as an explicit retuning guideline according to the user's preference for performance or robustness. Simulation and laboratory water tank experiment validate the tuning efficacy and a coal mill temperature control test depicts a promising prospective of the proposed method in process control practice.
64 citations
TL;DR: The synthesis of porous and hollow MoO3 (p-h-MoO3) microspheres via the oxidation of MoS2 microsphere templates, which are obtained via self-assembly of Mo S2 nanosheets under hydrothermal conditions are reported.
Abstract: The development of a high-performance sensing material for the detection of ammonia gas is of significant importance due to its wide industrial presence and potential hazard risks In this article, we report the synthesis of porous and hollow MoO3 (p-h-MoO3) microspheres via the oxidation of MoS2 microsphere templates, which are obtained via self-assembly of MoS2 nanosheets under hydrothermal conditions The composition and morphology of the p-h-MoO3 microspheres are systematically characterized via microscopic and spectroscopic techniques, and our sensing tests reveals that p-h-MoO3 possesses ultrahigh responsiveness to ammonia gas, which can be further optimized via the selection of a suitable oxidation temperature and time Additionally, the p-h-MoO3 shows minimal responses to other gaseous molecules, thereby demonstrating significant selectivity toward ammonia The sensing mechanism of p-h-MoO3 toward ammonia is further investigated to identify the origin of its ultrahigh sensitivity and selectivity via X-ray photoelectron spectroscopy and diffuse reflectance Fourier transform infrared spectroscopy
49 citations
TL;DR: It is proved that the proposed AFNTSM can guarantee finite-time convergence and zero tracking error for the quadrotor attitude control and can achieve faster convergence and stronger robustness in line with theoretical analysis.
Abstract: As one type of unmanned aerial vehicles, the quadrotor typically suffers from payload variations, system uncertainties, and environmental wind disturbances, which significantly deteriorate its attitude control performance. To provide high-speed, accurate, and robust attitude tracking performance for the quadrotor, an adaptive fast nonsingular terminal sliding mode (AFNTSM) controller is proposed in this article. The proposed AFNTSM controller combines the advantages of fast nonsingular terminal sliding mode (FNTSM), integral sliding mode, and adaptive estimation techniques, which are effective to achieve the desired tracking performance and suppress control signal chattering. Furthermore, unlike conventional methods, the adaptive estimation removes the requirements for the upper bound information of the disturbances. It is proved that the proposed AFNTSM can guarantee finite-time convergence and zero tracking error for the quadrotor attitude control. Finally, comparative study with the FNTSM control only and conventional sliding mode control is conducted through experiments and the results demonstrate that the proposed AFNTSM can achieve faster convergence and stronger robustness in line with theoretical analysis.
49 citations
TL;DR: This article proposes a more reasonable and feasible method based on a dual-view scene with calibration-free gaze direction that is feasible and better than the state-of-the-art methods based on multiple widely used metrics.
Abstract: Driver attention estimation is one of the key technologies for intelligent vehicles The existing related methods only focus on the scene image or the driver's gaze or head pose The purpose of this article is to propose a more reasonable and feasible method based on a dual-view scene with calibration-free gaze direction According to human visual mechanisms, the low-level features, static visual saliency map, and dynamic optical flow information are extracted as input feature maps, which combine the high-level semantic descriptions and a gaze probability map transformed from the gaze direction A multiresolution neural network is proposed to handle the calibration-free features The proposed method is verified on a virtual reality experimental platform that collected more than 550 000 samples and obtained a more accurate ground truth The experiments show that the proposed method is feasible and better than the state-of-the-art methods based on multiple widely used metrics This study also provides a discussion of the effects of different landscapes, times, and weather conditions on the performance
48 citations
TL;DR: A design methodology to employ antiparallel windings to smooth the coupling coefficients variation over different positions by reducing the coupling coefficient at central positions and enhancing it at boundary positions is proposed.
Abstract: Free positioning wireless charging for consumer electronics allows the devices to be charged at arbitrary positions and angles to improve user experience. However, a user-initiated sudden movement of the device during charging can cause hazards due to the abrupt variation of the coupling coefficient. To solve this issue, the coupling coefficient variation at different positions should be mitigated, which is also good for the design and high-efficiency operation of power electronics converters. This article proposes a design methodology to employ antiparallel windings to smooth the coupling coefficient variation over different positions by reducing the coupling coefficient at central positions and enhancing it at boundary positions. Two optimization methods are proposed: turn-by-turn optimization and winding-by-winding optimization. A design flow is offered. The hexagonal coil is compared with the square coil and proved to achieve better performance than the latter. An experimental prototype is implemented to validate the effectiveness of the proposed design methodology.
46 citations
TL;DR: The performance of active disturbance rejection control (ADRC) algorithms can be limited in practice by high-frequency measurement noise, so this problem is addressed by transforming the high-gain extended state observer (ESO) into a new cascade observer structure.
Abstract: The performance of active disturbance rejection control (ADRC) algorithms can be limited in practice by high-frequency measurement noise In this article, this problem is addressed by transforming the high-gain extended state observer (ESO), which is the inherent element of ADRC, into a new cascade observer structure Set of experiments, performed on a dc–dc buck power converter system, show that the new cascade ESO design, compared to the conventional approach, effectively suppresses the detrimental effect of sensor noise overamplification while increasing the estimation/control performance The proposed design is also analyzed with a low-pass filter at the converter output, which is a common technique for reducing measurement noise in industrial applications
46 citations
TL;DR: This article presents a low-frequency adaptive F SMPC (AMPC) stabilized based on Lyapunov stability theory to overcome the design problems of FSMPC.
Abstract: Despite being cost-effective, seven-level Modified Packed U-Cell (MPUC7) active rectifier tends to be unstable due to unequal dc-links. Thus, a multiobjective controller is required to stabilize voltages and currents besides preserving efficiency and power quality. While conventional finite-set model predictive control (FSMPC) can deal with the multiobjective problem, it cannot assure the system stability, and its weighing factors tuning significantly becomes tiresome as the number of objectives increases. This article presents a low-frequency adaptive FSMPC (AMPC) stabilized based on Lyapunov stability theory to overcome the design problems of FSMPC. AMPC handles four control objectives and a decoupled stability objective. The control objectives assure the standard performance of MPUC7 in terms of switching losses, d v /d t , THD, and capacitors ripple. The stability objective guarantees the rectifier reliability under unstable conditions. The weighting factors in AMPC are floating to tackle the tuning challenges where a radial basis function neural network controller (RBFC) adjusts their variations. RBFC is trained by a novel self-training method including particle swarm optimization (PSO) algorithm and some mathematical analyses without using any training data. Experimental and simulation tests also evaluate AMPC in different conditions to confirm its reliability in fulfilling the desired objectives.
45 citations
TL;DR: This article focuses on the control problem of a 5 degrees of freedom (DOF) offshore crane in 3-D space with persistent ship yaw and roll perturbations and proposes an effective output feedback control method that is the first control method designed for 5-DOF offshore cranes without any linearization, which only uses output signals.
Abstract: In practice, offshore cranes are effective transportation tools used on ships. Different from land-fixed cranes, offshore cranes work in the noninertial frame, which are usually affected by different disturbances. Therefore, the control problem of offshore cranes is much more difficult . Till now, only few control methods have been proposed for offshore cranes, which are usually designed for planar offshore cranes, while the more practical three-dimensional (3-D) movements are ignored . Considering these facts, in this article, we focus on the control problem of a 5 degrees of freedom (DOF) offshore crane in 3-D space with persistent ship yaw and roll perturbations and propose an effective output feedback control method. Specifically, we first present an elaborate coordinate transformation method to deal with ship perturbations. Then an energy-like function is constructed based on the transformed model, and then by designing some auxiliary signals, an output feedback method is designed with rigorous mathematical analysis to prove the closed-loop asymptotic stability results. As far as we know, the proposed method is the first control method designed for 5-DOF offshore cranes without any linearization, which only uses output signals. Finally, experimental results are included to verify the performance of the proposed method.
TL;DR: This paper introduces a sensorless model predictive control (MPC) scheme for a grid-connected inverter with an inductive-capacitive-inductive (LCL) filter using only the grid-side current measurement.
Abstract: This article introduces a sensorless model predictive control (MPC) scheme for a grid-connected inverter with an inductive–capacitive–inductive ( LCL ) filter using only the grid-side current measurement. A state estimator and a disturbance observer are designed based on the Lyapunov stability theory to reduce the number of sensors and to eliminate the steady-state error. A cost function penalizing the state tracking error is used for the MPC design, and the optimal weights of the cost function are systematically obtained by solving a linear matrix inequality (LMI)-based optimization problem. The variation in grid impedance is taken into account in the LMI optimization. The stability analysis of the overall system is presented, and the frequency responses of the closed-loop and open-loop systems are presented to verify suppression of the filter resonance frequency component. The effectiveness and feasibility of the proposed controller are validated through frequency response analysis and comparative simulation results. Experimental results are also presented to demonstrate the efficacy of the proposed control scheme compared to the linear quadratic regulator method.
TL;DR: The numerical study and the experimental data both demonstrate that the proposed automated tuning method is efficient in terms of required tuning iterations, robust to disturbances, and results in improved tracking.
Abstract: In this article, we propose a performance-based autotuning method for cascade control systems, where the parameters of a linear axis drive motion controller from two control loops are tuned jointly. Using Bayesian optimization as all parameters are tuned simultaneously, the method is guaranteed to converge asymptotically to the global optimum of the cost. The data-efficiency and performance of the method are studied numerically for several training configurations and compared numerically to those achieved with classical tuning methods and to the exhaustive evaluation of the cost. On the real system, the tracking performance and robustness against disturbances are compared experimentally to nominal tuning. The numerical study and the experimental data both demonstrate that the proposed automated tuning method is efficient in terms of required tuning iterations, robust to disturbances, and results in improved tracking.
TL;DR: The multithread dynamic optimization method with fractional-order model and the unscented Kalman filter and the Gaussian linear models based on parameters of six commonly used open-circuit-voltage models are proposed to estimate SOC and SOH.
Abstract: Accurate estimation of state-of-charge (SOC) and state-of-health (SOH) is extremely important for the state diagnosis of power batteries, which is related to the energy efficiency and safety of electric vehicles. However, in order to represent the signal noises of sensors, the most commonly used method based on Kalman filter introduces the random Gaussian noise into the estimation, which causes the uncertainty of the estimation results. In this article, the multithread dynamic optimization method is proposed to solve the problem. In addition, the fractional-order model and the unscented Kalman filter are used in SOC estimation. The Gaussian linear models based on parameters of six commonly used open-circuit-voltage models are proposed to estimate SOH. Finally, the dynamic stress test current condition and four lithium-ion batteries are implemented to verify the effectiveness of the proposed method in the experiment. For SOC estimation, root-mean-square error (RMSE) of the proposed method is 0.098 and the average value of the six models is 0.123, thus the proposed method improves the estimation accuracy by 20.32%. For SOH estimation, we compare the smallest RMSE of the six models and that of the proposed method for four experimental batteries, thus the average improvement of accuracy is 25.44%.
TL;DR: A speed-current single-loop control with q-axis current constrained based on time-varying second-order nonlinear disturbance observer is constructed by a novel finite-time controller for speed regulation of the PMSM system, which can balance well between the overcurrent protection and dynamic performance.
Abstract: A novel finite-time control with q -axis current constrained based on time-varying second-order nonlinear disturbance observer is investigated to improve the performance of overcurrent protection and disturbance rejection for permanent magnet synchronous motor (PMSM) system. In general, the hardware could be damaged by a large transient current for achieving high-precision tracking performance when PMSM starts up. To this end, a speed-current single-loop control with q-axis current constrained is constructed by a novel finite-time controller for speed regulation of the PMSM system, which can balance well between the overcurrent protection and dynamic performance. The estimated peak generated by the high gain to ensure a precise accuracy will be integrated into the control system at the initial moment in the traditional nonlinear disturbance observer. Taking this into account, parameter uncertainties, nonmodeled dynamics, and estimated peak at the initial moment of the PMSM system are estimated by a time-varying second-order nonlinear disturbance observer. Finally, rigorous stability analysis is established for the proposed composite strategy. Comparative simulations and experiments are designed on proportion integration differentiation, sliding mode control (SMC), and the proposed method. Results demonstrate that the proposed method has better robustness and overcurrent protection property.
TL;DR: The proposed three-level efficiency optimized EMS based on the dual reward functions Q-learning algorithm can effectively improve the energy efficiency of the system, and can slow down the aging of the fuel cell by reducing its operating stress.
Abstract: A reasonably designed energy management strategy (EMS) can guarantee the safe and stable operation of fuel cell hybrid electric vehicle (FCHEV). To optimize the energy conversion efficiency of FCHEV, this research proposes a three-level efficiency optimized EMS based on the dual reward functions Q-learning algorithm. Focused on the system overall efficiency, a hardware-in-the-loop experimental platform was built first to compare the effectiveness between the proposed EMS and other existed methods. The results shown that compared with other state-of-art methods, the proposed strategy can effectively improve the energy efficiency of the system, and can slow down the aging of the fuel cell by reducing its operating stress. To further verify the effectiveness of the proposed strategy, varying driving loads profile were tested based on a 1.2-kW hybrid electric vehicle developed in the laboratory. The FCHEV real-time experiment results indicated that the proposed EMS can achieve the average load power matching error of 0.19 W and can optimize the system average overall system efficiency to 52%. The proposed method can help to contribute to the massive commercialization and implementation of the FCHEV.
TL;DR: A distributed event-triggered power sharing control strategy that adaptively regulates the virtual impedances at both fundamental positive/negative sequence and harmonic frequencies and accurately share the reactive, unbalanced, and harmonics powers among distributed generation units is proposed.
Abstract: For several reasons, particularly due to the mismatch in the feeder impedance, accurate power sharing in islanded microgrids is a challenging task. To get around this problem, a distributed event-triggered power sharing control strategy is proposed in this article. The suggested technique adaptively regulates the virtual impedances at both fundamental positive/negative sequence and harmonic frequencies and, therefore, accurately share the reactive, unbalanced, and harmonics powers among distributed generation units. The proposed method requires no information of feeder impedance and involves exchanging information among units at only event-triggered times, which reduces the communication burden without affecting the system performance. The stability and interevent interval are analyzed in this article. Finally, experimental results are presented to validate the effectiveness of the proposed scheme.
TL;DR: This letter describes two improved 13-level inverters based on switched-capacitor that inherit various advantages of the original structure, such as a high boost factor of 6, self-balanced capacitor voltages, and reduced voltage ripples.
Abstract: This letter describes two improved 13-level inverters based on switched-capacitor. Compared with their original structure, which is published recently, one less high-voltage capacitor is required in the proposed inverters and the blocking voltage of their inverting half-bridge is reduced by half. In addition, the new inverters inherit various advantages of the original structure, such as a high boost factor of 6, self-balanced capacitor voltages, and reduced voltage ripples. Circuit description, operation principle, hybrid PWM modulation, and capacitor voltage ripples are analyzed and the feasibility of the proposed inverters is finally verified by experimental results.
TL;DR: For robot manipulators subject to unmeasurable/uncertain plant parameters, this paper designs a new adaptive motion controller, which ensures positioning errors to converge to zero and provides accurate gravity compensation.
Abstract: For robot manipulators subject to unmeasurable/uncertain plant parameters, this article designs a new adaptive motion controller, which ensures positioning errors to converge to zero and provides accurate gravity compensation. Meanwhile, specific motion constraints are also satisfied during the entire control process. Additionally, the proposed controller is further extended to address output feedback control without velocity measurement/numerical differential operations. A useful feature of this article is that neither complicated gain constraints nor the upper/lower bounds of model parameters/matrices in the dynamics are required in controller design and analysis, which greatly facilitates practical applications. Meanwhile, by introducing a nonlinear auxiliary term (related to motion constraints and error signals) into the proposed controllers, all links accurately reach their desired positions without exceeding the preset constraints, while the gravity vector is estimated online to eliminate static errors. Additionally, the asymptotic stability of the system equilibrium point is strictly proven; more importantly, the difficulty of stability analysis is significantly decreased based on the elaborately constructed Lyapunov function candidate. Compared with existing controllers, the main merits of the designed control schemes include fewer control gain conditions, more concise closed-loop stability analysis, and higher safety satisfying specific constraints. Finally, some hardware experiments are carried out to validate the performance of the presented controllers.
TL;DR: A novel direct modulation pattern control (DMPC) method is proposed to provide the further discussion on the lower switching frequency and the better harmonic current suppression in multiphase permanent magnet synchronous motors.
Abstract: The additional harmonic currents in multiphase permanent magnet synchronous motors (PMSMs) have been widely discussed and suppressed by the virtual vectors (VVs). However, the concept of VVs would result in an increasing in the switching frequency and losing the controllability in the harmonic subspace. In this article, a novel direct modulation pattern control (DMPC) method is proposed to provide the further discussion on the lower switching frequency and the better harmonic current suppression. First, a deadbeat control concept is applied to calculate the reference voltage vectors in torque production. In dual three-phase PMSM, there are several switching patterns which could generate the reference voltage vector. The designs of these switching patterns are determined according to the demand. In fact, two design concepts under the structure of DMPC is proposed. One is called the low switching frequency design. The control sets of this design is several switching patterns with only one switching signal. Another is called the low THD design. The control sets of this design is two switching patterns with opposite harmonic voltage vectors. Second, the influence of these different switching patterns in the xy currents is optimized by a cost function. Actually, there are two types of cost function. One is a multiobjective cost function, which is designed to regulate both the amplitude of switching patterns and suppress the xy currents. Another is derived from the first cost function that regulates only the xy currents. The amplitude is determined directly in the voltage vector calculation. Finally, the experimental results show a good performance of these control strategies, in terms of the αβ currents production, the xy currents and the switching frequency reduction.
TL;DR: To effectively reduce the magnetic noise, the effect of structure parameters on the longitudinal and transverse magnetic noise is analyzed, and the optimized parameters are obtained and show that the longitudinal magnetic noise decreases with the increasing aspect ratio and stabilize eventually.
Abstract: Magnetic field shields are important for electronic equipment, ultrahigh-sensitivity sensors, and electrical instruments. For ultrahigh-sensitivity atomic sensors, in particular, ferrite shields with low intrinsic magnetic noise are widely used. In this article, the calculation methods of longitudinal and transverse magnetic noise, which are calculated by loss, are analyzed. The experimental results confirm the feasibility of the model. Using the loss separation method, it is proved that the loss of ferrite magnetic shielding is mainly hysteresis loss, which is below 100 Hz. To effectively reduce the magnetic noise, we analyze the effect of structure parameters on the longitudinal and transverse magnetic noise, and the optimized parameters are obtained. The results show that the longitudinal magnetic noise decreases with the increasing aspect ratio and stabilize eventually. When the aspect ratio exceeds 1, the transverse magnetic noise remains practically unchanged. When the external diameter is fixed, by optimizing the thickness of the magnetic shield, the optimal solution for the longitudinal and transverse magnetic noise is obtained.
TL;DR: It is shown that the tracking error converges to an ultimate domain within the finite-time sense under the proposed self-triggered STA by using the strict Lyapunov function approach.
Abstract: This article is concerned with the design of a super-twisting algorithm (STA) based sliding mode controller for permanent magnet synchronous motor (PMSM) speed regulation system under the self-triggered mechanism. By using the strict Lyapunov function approach, it is shown that the tracking error converges to an ultimate domain within the finite-time sense under the proposed self-triggered STA. A feasible self-triggered strategy is designed for both cases with and without external perturbation. Moreover, a nonlinear optimization problem is formulated in terms of the tradeoff between the ultimate domain and the communication burden. The optimized STA gains are obtained by solving the above-formulated optimization problem via a particle swarm optimization algorithm. Finally, the applicability of the proposed self-triggered STA for PMSM is verified by simulation and experiment results.
TL;DR: A knowledge distillation framework, entitled KDnet-RUL, to compress a complex LSTM-based method for RUL prediction and demonstrates that the proposed method significantly outperforms state-of-the-art KD methods.
Abstract: Machine remaining useful life (RUL) prediction is vital in improving the reliability of industrial systems and reducing maintenance cost Recently, long short-term memory (LSTM) based algorithms have achieved state-of-the-art performance for RUL prediction due to their strong capability of modeling sequential sensory data In many cases, the RUL prediction algorithms are required to be deployed on edge devices to support real-time decision making, reduce the data communication cost, and preserve the data privacy However, the powerful LSTM-based methods which have high complexity cannot be deployed to edge devices with limited computational power and memory To solve this problem, we propose a knowledge distillation framework, entitled KDnet-RUL, to compress a complex LSTM-based method for RUL prediction Specifically, it includes a generative adversarial network based knowledge distillation (GAN-KD) for disparate architecture knowledge transfer, a learning-during-teaching based knowledge distillation (LDT-KD) for identical architecture knowledge transfer, and a sequential distillation upon LDT-KD for complicated datasets We leverage simple and complicated datasets to verify the effectiveness of the proposed KDnet-RUL The results demonstrate that the proposed method significantly outperforms state-of-the-art KD methods The compressed model with 128 times less weights and 462 times less total float point operations even achieves a comparable performance with the complex LSTM model for RUL prediction
TL;DR: By flexibly adjusting the transmission power of HBs in different modes, all the HBs are able to avoid overmodulation, and single-phase CHB PV grid-connected inverter can still operate normally even if the maximum powers among PV panels are seriously unbalanced.
Abstract: With the characteristics of module-level maximum power point tracking, module-level monitoring, and panel shut- off , single-phase cascaded H-bridge (CHB) inverter has outstanding advantages applied to household photovoltaic (PV) power generation occasion. However, unbalanced output powers among PV panels is an inherent problem of single-phase CHB PV inverter, which will make the H-bridges (HBs) with higher powers overmodulation, resulting in deteriorated grid current and even system instability. Aiming at this issue, this article proposes a power adaptive control strategy, which divides system operation into three modes, and calculates modulation waveforms by using different methods in different modes. By flexibly adjusting the transmission power of HBs in different modes, all the HBs are able to avoid overmodulation, and single-phase CHB PV grid-connected inverter can still operate normally even if the maximum powers among PV panels are seriously unbalanced. The effectiveness of the proposed control strategy is verified by simulation and experimental results.
TL;DR: This article investigates the command filtered backstepping synchronization control (CFBSC) method for a servo system driven by two motors synchronously, and the effectiveness of the proposed controller is validated through experiments.
Abstract: In dual-motor servo systems, several factors seriously affect the tracking performance especially in high-speed and high-accuracy situations, which include machinery flexibilities, torque disturbance, unmodeled dynamics, and motor parameter differences. Given these factors, this article investigates the command filtered backstepping synchronization control (CFBSC) method for a servo system driven by two motors synchronously. Command filters are used to deal with the virtual control signals in backstepping design process to avoid the computational burden causing by repeated derivatives, and a compensation system is applied to reduce the tracking error. Adaptive control is used to compensate the torque disturbance and unmodeled dynamics. In addition, the speed and torque synchronization control signals are designed to guarantee high synchronization performance. The stability of the dual-motor servo system is proved. And the effectiveness of the proposed controller is validated through experiments.
TL;DR: A novel bidirectional fuzzy brain emotional learning (BFBEL) controller is proposed to control a class of uncertain nonlinear systems such as the quadcopter unmanned aerial vehicle (QUAV).
Abstract: A novel bidirectional fuzzy brain emotional learning (BFBEL) controller is proposed to control a class of uncertain nonlinear systems such as the quadcopter unmanned aerial vehicle (QUAV). The proposed BFBEL controller is nonmodel-based and has a simplified fuzzy neural network structure and adapts with a novel bidirectional brain emotional learning algorithm. It is applied to control all six degrees-of-freedom of a QUAV for accurate trajectory tracking and to handle the payload uncertainties and disturbances in real-time. The trajectory tracking performance and the ability to handle the payload uncertainties are experimentally demonstrated on a QUAV. The experimental results show a superior performance and rapid adaptation capability of the proposed BFBEL controller. The proposed BFBEL controller can be used for the commercial drone applications.
TL;DR: By employing the backstepping technique, the proposed adaptive control strategy guarantees that a single adaptive control law can be used for accurate motion control of aerial vehicles with a wide range of inertial properties, without the need for retuning control gains or other parameters.
Abstract: In this article, we propose a solution to the problem of path following for a quadcopter aircraft with unknown vehicle parameters (mass and moment of inertia) and external disturbances By employing the backstepping technique, the proposed adaptive control strategy guarantees the following: the quadcopter is globally steered toward, and kept within, an arbitrarily small neighborhood of a desired smooth path, achieving global uniformly ultimately boundedness; compared to trajectory tracking, a smoother convergence is obtained as the control actuation signals (thrust force and torque) are bounded with respect to the position error, and the designed timing law ensures that the desired path starts to move only when the vehicle gets close to the desired path; and a single adaptive control law can be used for accurate motion control of aerial vehicles with a wide range of inertial properties, without the need for retuning control gains or other parameters Moreover, the controller is also made robust to external constant and slowly time-varying disturbances through the design of disturbance estimators To demonstrate the effectiveness and performance of the proposed control strategies, simulation and experimental results are presented and analyzed
TL;DR: This article presents a method to reduce the torque ripple in an 8/6 four-phase switched reluctance motor (SRM) by introducing a nonlinear modulating factor dependent on the rotor position and magnitude of the phase currents that manipulates the currents in two adjacent phases during commutation to maintain the net torque constant.
Abstract: This article presents a method to reduce the torque ripple in an 8/6 four-phase switched reluctance motor (SRM). The proposed scheme introduces a nonlinear modulating factor dependent on the rotor position and magnitude of the phase currents. This factor manipulates the currents in two adjacent phases during commutation and reduces the torque ripple effectively. Unlike the conventionally available torque-sharing functions, the proposed method instantaneously modulates every phase current obtained mathematically based on the other phase current in order to maintain the net torque constant. The proposed method requires minimal offline analysis and offers maximum possible torque with a minimal ripple. The method is simple and easy to implement due to a low computational burden. The proposed algorithm is implemented using MATLAB/Simulink software and is also validated experimentally on a 0.6-hp 8/6 SRM using a field-programmable-gate-arrays-based hardware setup developed in the laboratory. Typical results are presented and compared with the existing techniques. A torque ripple of $\approx 8\%$ has been achieved.
TL;DR: A novel double-stacked autoencoder (DSAE) is proposed for a fast and accurate judgment of power transformer health conditions with an imbalanced data structure and can achieve a fairly reliable diagnosis with a higher accuracy and less time than the other methods.
Abstract: Artificial intelligence is the general trend in the field of power equipment fault diagnosis. However, limited by operation characteristics and data defects, the application of the intelligent diagnosis method in power transformers is still in the initial stage. To fill this research gap, in this article, a novel double-stacked autoencoder (DSAE) is proposed for a fast and accurate judgment of power transformer health conditions with an imbalanced data structure. Three problems affecting the diagnosis effectiveness are overcome by a DSAE framework, an aging-tolerance criterion, and an advanced sparse deep clustering network. The proposed DSAE method is validated by two case studies based on an actual power transformer dataset. The results indicate that the proposed DSAE method can achieve a fairly reliable diagnosis with a higher accuracy and less time than the other methods, which demonstrates the superiority and effectiveness of the proposed approach.
TL;DR: A novel robust control strategy for three-phase power converters operated under unbalanced grid conditions is presented, in which an adaptive observer is applied to estimate the positive and negative sequences of the grid voltage.
Abstract: This article proposes a novel robust control strategy for three-phase power converters operated under unbalanced grid conditions. A consolidated control objective is obtained in the stationary $\alpha \beta$ frame, which can be flexibly adjusted according to the degree of oscillation in the active and reactive powers and the balance of the three-phase current. Based on the dynamics of the converter and control objective, a control scheme in a cascaded framework is presented, in which an adaptive observer is applied to estimate the positive and negative sequences of the grid voltage. In the current tracking loop, a super-twisting algorithm current controller coupled with a super-twisting differentiator is implemented to track the current references, featuring rapid dynamics, and improved robustness. Additionally, in the voltage regulation loop, an effective composite controller is developed to regulate the dc-link voltage, where a super-twisting observer is used to estimate the load disturbance, thereby improving the performance of the converter. The experimental results are provided to confirm the effectiveness and superiority of the proposed control strategy.