Abstract: The development of machine learning in complex system is hindered by two problems nowadays.The first problem is the inefficiency of exploration in state and action space, which leads to the data-hungry of some state-of-art data-driven algorithm.The second problem is the lack of a general theory which can be used to analyze and implement a complex learning system.In this paper, we proposed a general methods that can address both two issues.We combine the concepts of descriptive learning, predictive learning, and prescriptive learning into a uniform framework, so as to build a parallel system allowing learning system improved by self-boosting.Formulating a new perspective of data, knowledge and action, we provide a new methodology called parallel learning to design machine learning system for real-world problems.
Abstract: In this paper, we summarize recent progresses made in deep learning based acoustic models and the motivation and insights behind the surveyed techniques. We first discuss models such as recurrent neural networks (RNNs) and convolutional neural networks (CNNs) that can effectively exploit variablelength contextual information, and their various combination with other models. We then describe models that are optimized end-to-end and emphasize on feature representations learned jointly with the rest of the system, the connectionist temporal classification (CTC) criterion, and the attention-based sequenceto-sequence translation model. We further illustrate robustness issues in speech recognition systems, and discuss acoustic model adaptation, speech enhancement and separation, and robust training strategies. We also cover modeling techniques that lead to more efficient decoding and discuss possible future directions in acoustic model research.
Abstract: Images captured in hazy or foggy weather conditions can be seriously degraded by scattering of atmospheric particles, which reduces the contrast, changes the color, and makes the object features difficult to identify by human vision and by some outdoor computer vision systems. Therefore image dehazing is an important issue and has been widely researched in the field of computer vision. The role of image dehazing is to remove the influence of weather factors in order to improve the visual effects of the image and provide benefit to post-processing. This paper reviews the main techniques of image dehazing that have been developed over the past decade. Firstly, we innovatively divide a number of approaches into three categories: image enhancement based methods, image fusion based methods and image restoration based methods. All methods are analyzed and corresponding sub-categories are introduced according to principles and characteristics. Various quality evaluation methods are then described, sorted and discussed in detail. Finally, research progress is summarized and future research directions are suggested.
Abstract: The rapid development of location-based social networks (LBSNs) provides people with an opportunity of better understanding their mobility behavior which enables them to decide their next location. For example, it can help travelers to choose where to go next, or recommend salesmen the most potential places to deliver advertisements or sell products. In this paper, a method for recommending points of interest (POIs) is proposed based on a collaborative tensor factorization (CTF) technique. Firstly, a generalized objective function is constructed for collaboratively factorizing a tensor with several feature matrices. Secondly, a 3-mode tensor is used to model all users' check-in behaviors, and three feature matrices are extracted to characterize the time distribution, category distribution and POI correlation, respectively. Thirdly, each user's preference to a POI at a specific time can be estimated by using CTF. In order to further improve the recommendation accuracy, PCTF (Partitionbased CTF) is proposed to fill the missing entries of a tensor after clustering its every mode. Experiments on a real checkin database show that the proposed method can provide more accurate location recommendation.
Abstract: Nonlinear loads in the power distribution system cause non-sinusoidal currents and voltages with harmonic components. Shunt active filters (SAF) with current controlled voltage source inverters (CCVSI) are usually used to obtain balanced and sinusoidal source currents by injecting compensation currents. However, CCVSI with traditional controllers have a limited transient and steady state performance. In this paper, we propose an adaptive dynamic programming (ADP) controller with online learning capability to improve transient response and harmonics. The proposed controller works alongside existing proportional integral (PI) controllers to efficiently track the reference currents in the d -q domain. It can generate adaptive control actions to compensate the PI controller. The proposed system was simulated under different nonlinear (three-phase full wave rectifier) load conditions. The performance of the proposed approach was compared with the traditional approach. We have also included the simulation results without connecting the traditional PI control based power inverter for reference comparison. The online learning based ADP controller not only reduced average total harmonic distortion by 18.41 %, but also outperformed traditional PI controllers during transients.
Abstract: In this paper, a robust tracking control scheme based on nonlinear disturbance observer is developed for the self-balancing mobile robot with external unknown disturbances. A desired velocity control law is firstly designed using the Lyapunov analysis method and the arctan function. To improve the tracking control performance, a nonlinear disturbance observer is developed to estimate the unknown disturbance of the self-balancing mobile robot. Using the output of the designed disturbance observer, the robust tracking control scheme is presented employing the sliding mode method for the selfbalancing mobile robot. Numerical simulation results further demonstrate the effectiveness of the proposed robust tracking control scheme for the self-balancing mobile robot subject to external unknown disturbances.
Abstract: The inherent nature of energy, i.e., physicality, sociality and informatization, implies the inevitable and intensive interaction between energy systems and social systems. From this perspective, we define "social energy" as a complex sociotechnical system of energy systems, social systems and the derived artificial virtual systems which characterize the intense intersystem and intra-system interactions. The recent advancement in intelligent technology, including artificial intelligence and machine learning technologies, sensing and communication in Internet of Things technologies, and massive high performance computing and extreme-scale data analytics technologies, enables the possibility of substantial advancement in socio-technical system optimization, scheduling, control and management. In this paper, we provide a discussion on the nature of energy, and then propose the concept and intention of social energy systems for electrical power. A general methodology of establishing and investigating social energy is proposed, which is based on the ACP approach, i.e., "artificial systems" (A), "computational experiments" (C) and "parallel execution" (P), and parallel system methodology. A case study on the University of Denver (DU) campus grid is provided and studied to demonstrate the social energy concept. In the concluding remarks, we discuss the technical pathway, in both social and nature sciences, to social energy, and our vision on its future.
Abstract: The paper presents a new dual-mode nonlinear model predictive control (NMPC) scheme for continuous-time nonlinear systems subject to constraints on the state and control. The idea of control Lyapunov functions for nonlinear systems is used to compute the terminal regions and terminal control laws with some free-parameters in the dual-mode NMPC framework. The parameters of the terminal controller are selected offline to estimate the terminal region as large as possible; and the parameters are optimized online to gain optimality of the terminal controller with respect to given cost functions. Then a dual-mode NMPC algorithm with varying time-horizon is formulated for the constrained system. Recursive feasibility and closed-loop stability of this NMPC are established. The example of a spring-cart is used to demonstrate the advantages of the presented scheme by comparing to the dual-mode NMPC via the linear quadratic regulator (LQR) method.
Abstract: For a class of non-uniform output sampling hybrid system with actuator faults and bounded disturbances, an iterative learning fault diagnosis algorithm is proposed. Firstly, in order to measure the impact of fault on system between every consecutive output sampling instants, the actual fault function is transformed to obtain an equivalent fault model by using the integral mean value theorem, then the non-uniform sampling hybrid system is converted to continuous systems with timevarying delay based on the output delay method. Afterwards, an observer-based fault diagnosis filter with virtual fault is designed to estimate the equivalent fault, and the iterative learning regulation algorithm is chosen to update the virtual fault repeatedly to make it approximate the actual equivalent fault after some iterative learning trials, so the algorithm can detect and estimate the system faults adaptively. Simulation results of an electro-mechanical control system model with different types of faults illustrate the feasibility and effectiveness of this algorithm.
Abstract: Central nerve signal evoked by thoughts can be directly used to control a robot or prosthetic devices without the involvement of the peripheral nerve and muscles. This is a new strategy of human-computer interaction. A method of electroencephalogram (EEG) phase synchronization combined with band energy was proposed to construct a feature vector for pattern recognition of brain-computer interaction based on EEG induced by motor imagery in this paper. rhythm and beta rhythm were first extracted from EEG by band pass filter and then the frequency band energy was calculated by the sliding time window; the instantaneous phase values were obtained using Hilbert transform and then the phase synchronization feature was calculated by the phase locking value (PLV) and the best time interval for extracting the phase synchronization feature was searched by the distribution of the PLV value in the time domain. Finally, discrimination of motor imagery patterns was performed by the support vector machine (SVM). The results showed that the phase synchronization feature more effective in 4 s-7 s and the correct classification rate was 91.4 %. Compared with the results achieved by a single EEG feature related to motor imagery, the correct classification rate was improved by 3.5 and 4.3 percentage points by combining phase synchronization with band energy. These indicate that the proposed method is effective and it is expected that the study provides a way to improve the performance of the online real-time brain-computer interaction control system based on EEG related to motor imagery.
Abstract: In this paper a stable formation control law that simultaneously ensures collision avoidance has been proposed. It is assumed that the communication graph is undirected and connected. The proposed formation control law is a combination of the consensus term and the collision avoidance term (CAT). The first order consensus term is derived for the proposed model, while ensuring the Lyapunov stability. The consensus term creates and maintains the desired formation shape, while the CAT avoids the collision. During the collision avoidance, the potential function based CAT makes the agents repel from each other. This unrestricted repelling magnitude cannot ensure the graph connectivity at the time of collision avoidance. Hence we have proposed a formation control law, which ensures this connectivity even during the collision avoidance. This is achieved by the proposed novel adaptive potential function. The potential function adapts itself, with the online tuning of the critical variable associated with it. The tuning has been done based on the lower bound of the critical variable, which is derived from the proposed connectivity property. The efficacy of the proposed scheme has been validated using simulations done based on formations of six and thirty-two agents respectively.
Abstract: This paper presents a variable speed control strategy for wind turbines in order to capture maximum wind power. Wind turbines are modeled as a two-mass drive-train system with generator torque control. Based on the obtained wind turbine model, variable speed control schemes are developed. Nonlinear tracking controllers are designed to achieve asymptotic tracking for a prescribed rotor speed reference signal so as to yield maximum wind power capture. Due to the difficulty of torsional angle measurement, an observer-based control scheme that uses only rotor speed information is further developed for global asymptotic output tracking. The effectiveness of the proposed control methods is illustrated by simulation results.
Abstract: This paper presents a simple and systematic approach to design second order sliding mode controller for buck converters. The second order sliding mode control (SOSMC) based on twisting algorithm has been implemented to control buck switch mode converter. The idea behind this strategy is to suppress chattering and maintain robustness and finite time convergence properties of the output voltage error to the equilibrium point under the load variations and parametric uncertainties. In addition, the influence of the twisting algorithm on the performance of closed-loop system is investigated and compared with other algorithms of first order sliding mode control such as adaptive sliding mode control (ASMC), nonsingular terminal sliding mode control (NTSMC).In comparative evaluation, the transient response of the output voltage with the step change in the load and the start-up response of the output voltage with the step change in the input voltage of buck converter were compared. Experimental results were obtained from a hardware setup constructed in laboratory. Finally, for all of the surveyed control methods, the theoretical considerations, numerical simulations, and experimental measurements from a laboratory prototype are compared for different operating points. It is shown that the proposed twisting method presents an improvement in steady state error and settling time of output voltage during load changes.
Abstract: Wheeled mobile robots (WMRs) encounter unavoidable slippage especially on the low adhesion terrain such that the robots stability and accuracy are reduced greatly. To overcome this drawback, this article presents a neural network (NN) based terminal sliding mode control (TSMC) for WMRs where an augmented ground friction model is reported by which the uncertain friction can be estimated and compensated according to the required performance. In contrast to the existing friction models, the developed augmented ground friction model corresponds to actual fact because not only the effects associated with the mobile platform velocity but also the slippage related to the wheel slip rate are concerned simultaneously. Besides, the presented control approach can combine the merits of both TSMC and radial basis function (RBF) neural networks techniques, thereby providing numerous excellent performances for the closed-loop system, such as finite time convergence and faster friction estimation property. Simulation results validate the proposed friction model and robustness of controller; these research results will improve the autonomy and intelligence of WMRs, particularly when the mobile platform suffers from the sophisticated unstructured environment.
Abstract: In this paper, we studied the approximate sampleddata observer design for a class of stochastic nonlinear systems. Euler-Maruyama approximation was investigated in this paper because it is the basis of other higher precision numerical methods, and it preserves important structures of the nonlinear systems. Also, the form of Euler-Maruyama model is simple and easy to be calculated. The results provide a reference for sampled-data observer design method for such stochastic nonlinear systems, and may be useful to many practical control applications, such as tracking control in mechanical systems. And the effectiveness of the approach is demonstrated by a simulation example.
Abstract: The large inertia of a traditional power system slows down system's frequency response but also allows decent time for controlling the system. Since an autonomous renewable microgrid usually has much smaller inertia, the control system must be very fast and accurate to fight against the small inertia and uncertainties. To reduce the demanding requirements on control, this paper proposes to increase the inertia of photovoltaic (PV) system through inertia emulation. The inertia emulation is realized by controlling the charging/discharging of the direct current (DC)-link capacitor over a certain range and adjusting the PV generation when it is feasible and/or necessary. By well designing the inertia, the DC-link capacitor parameters and the control range, the negative impact of inertia emulation on energy efficiency can be reduced. The proposed algorithm can be integrated with distributed generation setting algorithms to improve dynamic performance and lower implementation requirements. Simulation studies demonstrate the effectiveness of the proposed solution.
Abstract: Since the efficiency of photovoltaic (PV) power is closely related to the weather, many PV enterprises install weather instruments to monitor the working state of the PV power system. With the development of the soft measurement technology, the instrumental method seems obsolete and involves high cost. This paper proposes a novel method for predicting the types of weather based on the PV power data and partial meteorological data. By this method, the weather types are deduced by data analysis, instead of weather instrument. A better fault detection is obtained by using the support vector machines (SVM) and comparing the predicted and the actual weather. The model of the weather prediction is established by a direct SVM for training multiclass predictors. Although SVM is suitable for classification, the classified results depend on the type of the kernel, the parameters of the kernel, and the soft margin coefficient, which are difficult to choose. In this paper, these parameters are optimized by particle swarm optimization (PSO) algorithm in anticipation of good prediction results can be achieved. Prediction results show that this method is feasible and effective.
Abstract: This paper focuses on synchronization of fractionalorder complex dynamical networks with decentralized adaptive coupling. Based on local information among neighboring nodes, two fractional-order decentralized adaptive strategies are designed to tune all or only a small fraction of the coupling gains respectively. By constructing quadratic Lyapunov functions and utilizing fractional inequality techniques, Mittag-Leffler function, and Laplace transform, two sufficient conditions are derived for reaching network synchronization by using the proposed adaptive laws. Finally, two numerical examples are given to verify the theoretical results.
IEEE/CAA Journal of Automatica Sinica
JCR Impact Factor 2020: 6.171 Rank：Top 11% (7/93), Category of Automation & Control Systems Quantile: The 1st (SCI Q1)
CiteScore 2020 : 11.2 Rank： Top 5% (Category of Computer Science: Information System) , Top 6% (Category of Control and Systems Engineering), Top 7% (Category of Artificial Intelligence)Quantile: The 1st (Q1)