In this paper, an attack-tolerant fuzzy path following control method is proposed for distributed drive electric vehicles subject to aperiodic denial-of-service (DoS) attacks based on an event-triggered output feedback framework. Firstly, to construct a framework for feasible controller design under DoS attacks, a switched interval type-2 fuzzy output feedback control framework is established with consideration of vehicle dynamics nonlinearity coupled with DoS attacks. Secondly, to guarantee the stability and desired path following performance of the vehicle closed-loop control system under DoS attacks, an attack-tolerant sufficient condition is derived by constructing piecewise Lyapunov functional. Thirdly, to balance control performance and network bandwidth utilization under DoS attacks, a resilient event-triggered fuzzy output feedback control method is proposed in terms of a set of linear matrix inequalities. Finally, experimental results validate the effectiveness and superiority of the proposed method in the aspect of path following accuracy and network resource conservation following accuracy compared with existing methods.

Due to inherent vulnerabilities and openness of the communication protocol, denial-of-service attacks may occur in the vehicle path tracking system to cause unreliable communication links. Thus, this paper explores a dynamic output feedback fuzzy path tracking control method for the intelligent electric vehicle under unreliable communication links. First, to establish a foundation for both communication analysis and controller design, an interval type-2 fuzzy dynamic output feedback control model is constructed to describe the vehicle path tracking system considering dynamic nonlinearities and measurement constraints. Second, to maintain acceptable data transmission efficiency under unreliable communication links, a switched event-triggered mechanism is proposed to regulate the communication scheduling according to the detection signal of denial-of-service attacks. Third, to preserve the exponential stability and path tracking performance of the vehicle control system under unreliable communications links, a novel co-design method is developed for the fuzzy dynamic output feedback controller and switched event-triggered strategy by employing the piecewise Lyapunov-Krasovskii functional approach. Finally, the experimental results demonstrate the effectiveness and superiority of the proposed control approach compared to existing path tracking control methods under unreliable communication links.

This work proposes a robust fault-tolerant path following control strategy for Autonomous Ground Vehicles (AGVs) subjected to network delays and actuator failures. Firstly, a Takagi-Sugeno (T-S) fuzzy model is developed to characterize the nonlinear vehicle dynamics, accounting for uncertainties in vehicle speed and tire cornering stiffness. Secondly, a stability condition is derived using linear matrix inequalities (LMIs) with expanded matrices to handle network-induced delays and data loss. Thirdly, a fault-tolerant control method integrating robust H-infinity performance is proposed to ensure path following accuracy and stability. Experimental results via hardware-in-the-loop tests demonstrate the effectiveness of the proposed controller in improving tracking performance and handling actuator failures under varying conditions.

Under open-network environments with constrained bandwidth, the vehicle suspension control systems are particularly susceptible to denial-of-service attacks, which can cause intermittent communication. To address this challenge, a resilient fuzzy control method is proposed for nonlinear suspension systems of in-wheel motor drive electric vehicles under intermittent event-triggered communication. Firstly, based on a nonlinear quarter-vehicle suspension model, a switched interval type-2 fuzzy suspension model is established to describe both the suspension nonlinear dynamics and intermittent communication under denial-of-service attacks. Secondly, to maintain effective communication under denial-of-service attacks, an intermittent event-triggered strategy with dual adaptive thresholds is proposed to alleviate communication resource constraints and mitigate the adverse effects of intermittent communication. Thirdly, to guarantee the suspension performance under denial-of-service attacks, a resilient fuzzy control method is proposed for vehicle suspension systems. The piecewise Lyapunov functions and matrix inequality are employed to ensure the exponential stability and desired performance requirements. Finally, in comparison with existing vehicle suspension control methods, the proposed resilient fuzzy control method demonstrates significant performance advantages by the hardware-in-the-loop experiments.

This work proposes a fractional-order compound steering control for lateral stabilization of dual motor drive electric vehicles (DDEVs) subject to multi-agent coupled game. Firstly, given that the compound steering involves the interactions between the active steering and differential torque, a closed-loop control framework-based multi-agent coupled game theory is proposed to coordinate the dynamic interaction information. Secondly, accounting for the complexity of nonlinear systems, a piecewise affine method is described to segmentally linearize the system and reduce the computational burden. Furthermore, the coupled game optimization problem for DDEVs with fuzzy nonlinearities is solved by integrating the dynamic programming strategy. Thirdly, considering that integer-order differential equations have limitations in describing complex characteristics of the vehicle dynamics, a fractional-order differential equation-based control strategy is developed to guarantee the stability of the control system by addressing the coupled game optimization problem of the vehicle dynamics. Finally, experimental results are performed to examine the effectiveness and merits of the proposed dynamic programming-based fractional-order compound steering control method in enhancing the lateral stabilization of DDEVs.

This article proposes an adjustable-error neural network (NN) approximator and incorporates it into the adaptive neural tracking controller design of uncertain nonlinear systems. Noted that the error between the unknown nonlinear function and the NN approximator cannot be adjusted under the traditional NN control framework, as it is solely determined by the selection of neurons, basis functions, and the estimation of the ideal weight vector. This inherent constraint compromises the precision of the NN approximation and the convergence accuracy of the tracking error. To improve the approximation accuracy of unknown nonlinear functions in adaptive neural control systems, an adjustable-error NN approximator is designed, in which the error between the approximator and the unknown nonlinear function can be adjusted by designed parameters. Based on the proposed NN approximator, an adaptive neural tracking controller is designed for a class of uncertain nonlinear systems, which achieves higher accuracy of the tracking error compared with traditional methods. The stability of the resulting closed-loop system is proved in the Lyapunov sense, and the convergence of the tracking error is also analyzed. The effectiveness of the proposed scheme is verified by simulation and experiment.

This work investigates the fault-prediction optimal output regulation problem for the structural reliability feedback (SRF) system, and it aims to design a reliability feedback controller that minimizes the probability of fault (PoF) of the SRF system. Distinguished from the existing feedback control, the tracking of the upper bound of the PoF is considered to ensure the fault-prediction in the feedback control. The proposed design converts the PoF tracking problem into the satisfaction of the generalized damage energy (GDE). Furthermore, the impact of inaccurate measurement is eliminated by tolerating the epistemic uncertainty via a novel probabilistic policy iteration (PI). Moreover, the uniformly ultimately bounded (UUB) condition of the SRF system is guaranteed by employing the subset method. Finally, comparative investigations are conducted to examine the superiority of the proposed approach.

Under extreme conditions, the yaw stabilization of the four-wheel-independent-drive electric vehicle (FWID-EV) is crucial for vehicle safety. This work proposes a flexible prescribed performance control (FPPC)-based Lorentzian-relaxation filtered adaptive dynamic programming (LRF-ADP) method to solve the cooperative differential game (CDG) between the active front steering (AFS) and the torque vectoring control (TVC). First, to guarantee the transient and steady-state performances of the vehicle, a flexible prescribed performance function is developed to deal with the control singularity. Second, to enhance the computational efficiency of the controller, a filtered Hamilton-Jacobi-Bellman equation is established with the dynamic-sample-size method and hysteresis switching strategy-based experience replay (ER) algorithm. Third, to ensure the convergence for the policy iteration (PI) of the controller, a Lorentzian-relaxation strategy is proposed to regulate the degrees of the relaxation. Moreover, to examine the effectiveness and practicability of the proposed method, the software-in-the-loop and hardware-in-the-loop tests are conducted under emergency maneuvers, respectively.

This article proposes the row-stochastic event-based quantized (RSEQ) algorithm to address the distributed optimization problem with multiple communication constraints, including limited communication costs and bandwidth. In RSEQ, a novel event-based dynamic quantizer is designed to resist the negative effects of communication constraints on the algorithm. The quantizer encompasses the event generator and the dynamic encoder/decoder, which collectively adapt the frequency and size of information sharing based on real-time state. The RSEQ only requires the construction of a row-stochastic weight matrix, which leads to lower conservatism compared to algorithms based on column-stochastic matrices. Additionally, the introduction of an acceleration term enables RSEQ to linearly converge to the globally optimal solution without the deployment of the average gradient estimator. Instead, a Perron vector estimator needs to be employed to counteract the unbalancedness of the directed network. With the effect of the event generator, the Perron vector estimator can also be left inactive after a certain number of iterations, which means that the transmission of only state information between agents can linearly converge to the global optimal solution under directed networks. Finally, the effectiveness of the algorithm is demonstrated through an economic dispatch problem in smart grids.

The air suspension is an advanced suspension system for vibration suppression of vehicles. However, the real-time controllability of the air suspension is weak due to the time-delay characteristics of the air spring. This study designs a novel magnetorheological semiactive air suspension (MSAS) system and examines the fault characteristics of the MSAS system to improve the performance of vibration suppression. First, the generalized fuzzy hysteresis model is novelly proposed to approximate the hysteresis nonlinearity of the magnetorheological fluid damper. Then, the MSAS model with various fault modes is constructed to study the dynamic performance of the MSAS system under different fault modes. Furthermore, the intermediate estimator is adopted to detect the generation of the sensor and actuator faults. Based on the fault estimation, a reinforcement learning-based fault-tolerant (RLF) controller is proposed to improve the dynamic performance of the MSAS system. Moreover, a double wishbone suspension is built to examine the effectiveness of the proposed RLF controller. Experimental results show that the dynamic performance of the MSAS system with the proposed RLF controller is improved in comparison with the MSAS system with the model-based controllers and the passive suspension.

In this paper, an event-triggered fuzzy security path following control problem is investigated for autonomous ground vehicles subject to aperiodic denial of service attacks. Firstly, a switched interval type-2 fuzzy model is established to depict the vehicle path following system, in which both the vehicle dynamic nonlinearities and the aperiodic denial of service attacks are well addressed. Secondly, to guarantee that the latest packets are sent out immediately at the end of the denial of service attacks, a novel attack-dependent event-triggered scheme is developed to improve the signal transmission efficiency and reduce the performance loss caused by denial of service attacks. Then, by constructing a piecewise Lyapunov function based on the average dwell time of the denial of service attacks, a security control method is proposed to guarantee the exponential stability and the path following performance of the switched fuzzy path following system. Finally, the superiority of the proposed control strategy is verified by experimental tests as compared with the current path following control methods.

Accurate and real-time acquisition of vehicular system dynamic states, road surface conditions, and motion states of surrounding participants is crucial for the safety, passenger comfort, and operational efficiency of autonomous vehicles (AVs) and connected automated vehicles (CAVs). In recent years, a significant amount of research has contributed to the field of state estimation for vehicles, roads, and pedestrians. From the systemwide perspective of intelligent transportation systems to a focused view on “vehicle-road-pedestrian”, this survey aims to provide a comprehensive review and summary of recent state estimation techniques for vehicle motion, road surface, and pedestrian motion. A thorough analysis of the reviewed literature, relevant datasets, evaluation metrics, and experimental platforms in this field is also conducted. Finally, existing challenges and future research directions about methods and performance evaluation are further discussed. This survey is expected to contribute to the advancement of research in dynamic state estimation of vehicle-road-pedestrian, thereby facilitating the development of efficient and safe intelligent transportation systems.

Transfer learning (TL) and generative adversarial networks (GANs) have been widely applied to intelligent fault diagnosis under imbalanced data and different working conditions. However, the existing data synthesis methods focus on the overall distribution alignment between the generated data and real data, and ignore the fault-sensitive features in the time domain, which results in losing convincing temporal information for the generated signal. For this reason, a novel gated recurrent generative TL network (GRGTLN) is proposed. First, a smooth conditional matrix-based gated recurrent generator is proposed to extend the imbalanced dataset. It can adaptively increase the attention of fault-sensitive features in the generated sequence. Wasserstein distance (WD) is introduced to enhance the construction of mapping relationships to promote data generation ability and transfer performance of the fault diagnosis model. Then, an iterative "generation-transfer" co-training strategy is developed for continuous parallel training of the model and the parameter optimization. Finally, comprehensive case studies demonstrate that GRGTLN can generate high-quality data and achieve satisfactory cross-domain diagnosis accuracy.

In the domain of continuous control, deep reinforcement learning (DRL) demonstrates promising results. However, the dependence of DRL on deep neural networks (DNNs) results in the demand for extensive data and increased computational cost. To address this issue, a novel hybrid actor-critic reinforcement learning (RL) framework is introduced. The proposed framework integrates the broad learning system (BLS) with DNN, aiming to merge the strengths of both distinct architectural paradigms. Specifically, the critic network employs BLS for rapid value estimation via ridge regression, while the actor network retains the DNN structure to optimize policy gradients. This hybrid design is generalizable and can enhance existing actor-critic algorithms. To demonstrate its versatility, the proposed framework is integrated into three widely used actor-critic algorithms-deep deterministic policy gradient (DDPG), soft actor-critic (SAC), and twin delayed DDPG (TD3), resulting in BLS-augmented variants. The experimental results reveal that all BLS-enhanced versions surpass their original counterparts in terms of training efficiency and accuracy. These improvements highlight the suitability of the proposed framework for real-time control scenarios, where computational efficiency and rapid adaptation are critical.

This article investigates the issue of privacy preservation in distributed optimization, where each node possesses a local private objective function and collaborates to minimize the sum of those functions. A novel dynamic average consensus-based distributed Newton algorithm is introduced to achieve consensus, optimality, and differential privacy. Each node utilizes its local gradient and Hessian as time-varying reference signals, facilitating information exchange with neighbors for tracking the average. To safeguard privacy, persistent Laplace noise is introduced into the exchanged data, affecting the estimated optimal solution, gradient, and Hessian averages. To counteract the noise’s impact, the internode coupling strength is adaptively reduced over time through decay factors, allowing for noise attenuation as the algorithm progresses. The algorithm’s convergence to the optimal solution, assuming global function smoothness and strong convexity, is theoretically proven. The algorithm’s accurate convergence to the optimal solution, assuming global function smoothness and strong convexity, is theoretically proven. Furthermore, the efficiency and reliability of the algorithm are empirically validated through simulations of an IEEE 14-bus test system.

The consideration of reliability in controller design is able to avoid the potential actuator faults from inappropriate strategies. This work presents an optimal reliability-critical controller to avoid potential actuator faults by developing a probabilistic adaptive dynamic programming (ADP) algorithm with the estimation of fault interruption. The proposed algorithm distinguishes from existing ADPs in that the structural reliability is considered in policy iteration, endowing the resultant controller with the capacity to avoid potential actuator faults. The algorithm relaxes the generalized damage energy-Hamilton–Jacobi–Bellman equation to a reliability-critical problem, which is solved by proposing a probabilistic policy iteration method. Instead of studying the stability regardless of physical damage, the effect of physical damage is considered in the system stability in the form of structural reliability, and the probabilistic policy iteration guarantees the optimal relation between the stability and structural reliability. Finally, the effectiveness of the proposed algorithm is verified by conducting experimental tests.

Wind power is of strategic importance for reducing carbon dioxide emissions, minimizing environmental pollution, and enhancing the sustainability of energy supply. Health monitoring of wind turbines is a crucial technology to ensure the quality of grid-connected power. Insufficient labeled data and class imbalance problems are two critical issues for intelligent fault diagnosis of wind turbines. In this article, an intelligent fault diagnosis method based on stacked capsule autoencoders is proposed to address the issues of inadequate labeled data and class imbalance. A prior knowledge-based convolution layer is applied to optimize the initialization of capsules, making it more conducive to learning spectral information. The pose representations of parts and objects can be improved, and a method for embedding spectral templates is proposed. The stacked capsule autoencoder in this study can learn partial templates unsupervised through likelihood estimation and establish the mapping between capsules and fault types. The experimental results, obtained from the CWRU dataset and a private dataset from a wind turbine drive-train simulation platform, demonstrate that the proposed method is robust to imbalanced and small-sized datasets. It can perform stable and effective unsupervised training by utilizing a sufficient amount of normal class data to expedite learning convergence.

This article focuses on the path tracking control problem for autonomous ground vehicles under switched triggered and sensor attacks. Firstly, an interval type-2 Takagi-Sugeno fuzzy model is established to effectively approximate the tire dynamic nonlinearities and varying velocity in the path tracking control system, in which the random deception attack encountered in the sensor is considered. Secondly, a novel switched triggered communication mechanism is presented to decrease the frequency of signal transmission and save the network resources. The switched triggered mechanism includes both the time-triggered mode and event-triggered mode, which obey a Bernoulli distribution. Then, based on a positive Lyapunov-Krasovskii functional and matrix inequalities, a set of conditions are developed for the path tracking controller design to achieve the asymptotic stability and performance requirements. Finally, experimental results are presented to evaluate and validate the performance of the proposed path tracking control method.

Offline reinforcement learning (ORL) has been getting increasing attention in robot learning, benefiting from its ability to avoid hazardous exploration and learn policies directly from precollected samples. Approximate policy iteration (API) is one of the most commonly investigated ORL approaches in robotics, due to its linear representation of policies, which makes it fairly transparent in both theoretical and engineering analysis. One open problem of API is how to design efficient and effective basis functions. The broad learning system (BLS) has been extensively studied in supervised and unsupervised learning in various applications. However, few investigations have been conducted on ORL. In this article, a novel incremental ORL approach with sparse broad critic approximation (BORL) is proposed with the advantages of BLS, which approximates the critic function in a linear manner with randomly projected sparse and compact features and dynamically expands its broad structure. The BORL is the first extension of API with BLS in the field of robotics and ORL. The approximation ability and convergence performance of BORL are also analyzed. Comprehensive simulation studies are then conducted on two benchmarks, and the results demonstrate that the proposed BORL can obtain comparable or better performance than conventional API methods without laborious hyperparameter fine-tuning work. To further demonstrate the effectiveness of BORL in practical robotic applications, a variable force tracking problem in robotic ultrasound scanning (RUSS) is investigated, and a learning-based adaptive impedance control (LAIC) algorithm is proposed based on BORL. The experimental results demonstrate the advantages of LAIC compared with conventional force tracking methods.

In the stereo matching task, the 3D convolution network can effectively aggregate the cost volume with the strong representation ability to model the spatial and depth dimensions but with the disadvantage of a high computational cost. In this letter, we revisit the 3D convolution network and its common variant, and then propose the Depth Shift Module (DSM) to model the cost volume in the depth dimension which could imitate the 3D convolution function with the computational complexity of the 2D convolution. The proposed DSM is easy to extend to present 3D cost aggregation methods in stereo matching with less inference time, lower computational complexity, and minor precision loss. Moreover, a novel compact but efficient stereo matching framework named HybridNet is proposed. This framework can hybridize the 2D convolution layer with the proposed DSM to effectively aggregate the cost volume. The proposed HybridNet achieves a better trade-off between the performance, computational complexity, and model size ( e.g. , 30% less than the size of AANet and 25% less than the size of PSMNet) in public open-source datasets ( e.g. , Scene Flow and KITTI Stereo 2015). The relevant code is available at https://github.com/GANWANSHUI/HybridNet .

This article proposes an observer-based discrete-time cascaded control (ODCC) strategy for lateral stabilization of Steer-by-Wire (SbW) vehicles with consideration of uncertainties and disturbances. First, for the observation of the sideslip angle and yaw rate, an information fusion-based unscented Kalman filter (IFUKF) is designed to reduce the negative effect from the variation of the parameters; Second, aiming to eliminate the errors of control variables for lateral stabilization of SbW vehicles, a discrete-time sliding mode predictive control (DSMPC) is presented to deal with matched and mismatched uncertainties and input constraint; Third, to reduce the tracking error between the actual front wheel steering angle and the desired one generated by the DSMPC, a combination of discrete-time fast terminal sliding mode and active disturbance rejection control is proposed to tackle the problems of parameter uncertainties and disturbances in the SbW system. Performance evaluations are conducted via both software-in-the-loop and hardware-in-the-loop to examine the availability and practicability of the ODCC strategy.

In this article, a generalized fuzzy subset (GFS) method is proposed to assess the time-varying multistate reliability of the perturbation failure coupling measurement system. First, a perturbation-failure coupling mechanism is designed to define the propagation chain of perturbations so as to integrate all the possible perturbations as the inputs of the GFS method. Second, to assess the time-varying multistate reliability, a GFS reliability model is constructed based on the composite limit state. Furthermore, the concept of the uncertain subset boundary is presented to conduct the reliability assessment via a group of embedded interval type-2 fuzzy sets. To address the deficiency of the GFS reliability model, a data-driven strategy is designed to establish the implicit relation between the limited expert knowledge and the membership function. Finally, the experimental tests are carried out to examine the superiority of the GFS method, and parametric studies are also conducted to study the reliability of the PFCM system.

With the consideration of actuator faults, including the unknown steering mechanism misalignments and motor traction losses, this article presents a fixed-time control protocol to follow reference paths and velocities for autonomous ground vehicles (AGVs) with preset performance constraints. To provide sufficient large boundaries for the initial states, the hyperbolic tangent function is employed to predefine the constraints with respect to the path-following and velocity control performance. Based on the homeomorphic mapping and barrier Lyapunov theorem, the fixed-time prescribed performance control (PPC) objective-integrated fault-tolerant scheme can be achieved for the controlled AGV. In comparison to three different fixed-time controllers without the fault-tolerant or PPC scheme, the hardware-in-the-loop (HIL) test results demonstrate that the proposed control protocol can always provide superior control performance for the AGV under various maneuvering conditions.

Due to its strong performance in handling uncertain and ambiguous data, the fuzzy k -nearest-neighbor method (FKNN) has realized substantial success in a wide variety of applications. However, its classification performance would be heavily deteriorated if the number k of nearest neighbors was unsuitably fixed for each testing sample. This study examines the feasibility of using only one fixed k value for FKNN on each testing sample. A novel FKNN-based classification method, namely, fuzzy KNN method with adaptive nearest neighbors (A-FKNN), is devised for learning a distinct optimal k value for each testing sample. In the training stage, after applying a sparse representation method on all training samples for reconstruction, A-FKNN learns the optimal k value for each training sample and builds a decision tree (namely, A-FKNN tree) from all training samples with new labels (the learned optimal k values instead of the original labels), in which each leaf node stores the corresponding optimal k value. In the testing stage, A-FKNN identifies the optimal k value for each testing sample by searching the A-FKNN tree and runs FKNN with the optimal k value for each testing sample. Moreover, a fast version of A-FKNN, namely, FA-FKNN, is designed by building the FA-FKNN decision tree, which stores the optimal k value with only a subset of training samples in each leaf node. Experimental results on 32 UCI datasets demonstrate that both A-FKNN and FA-FKNN outperform the compared methods in terms of classification accuracy, and FA-FKNN has a shorter running time.

This article proposes a novel improved adaptive event-triggered (AET) control algorithm for networked Takagi-Sugeno (T-S) fuzzy systems with asynchronous constraints. First, taking the limited bandwidth of the network into consideration, an improved AET mechanism is proposed to save the communication resource. Superior to the existing event-triggered mechanism, the improved AET scheme introduces two adjusting parameters, which further contribute to the economization of the communication resource. Second, with consideration of asynchronous premise variables, a reconstructed approach is applied to synchronize the time scales of membership functions of the fuzzy system and the fuzzy controller. Third, to derive a less conservative sufficient condition for the controller design, a new augmented Lyapunov-Krasovskii functional with event-triggered information and triple integral terms is constructed. Meanwhile, by applying a Bessel-Legendre inequality and extended reciprocally convex matrix inequality together, a new control algorithm is derived with less conservatism. Finally, simulations on a cart-damper-spring system are implemented to evaluate and verify the performance and advantages of the proposed algorithm.

While our recent deep fuzzy classifier DSA-FC, which stacks adversarial interpretable Takagi–Sugeno–Kang fuzzy subclassifiers, shares its promising classification, its training speed will become very slow and even intolerable for large-scale datasets, due to successive training on all training samples with their random gradient based updates along each layer of its stacked structure. In order to circumvent this bottleneck issue, a fast training algorithm FTA is developed in this study by downsizing fuzzy rules with the proposed gradient guided learning for each subclassifier at each layer of DSA-FC on large-scale datasets. The core of FTA is to assure fast training of each subclassifier at each layer of DSA-FC, which first generates first-order smooth gradient guided information by means of the proposed top-kfuzzy rules selected from all fuzzy rules in each subclassifier, and then quickly updates the current inputs in terms of such information, which will be taken as the inputs of the subclassifier at the next layer. Our theoretical analysis reveals that the proposed gradient guided learning indeed enhances the generalization capability of a deep fuzzy classifier with or without adversarial attacks on outputs. Experimental results on large datasets demonstrate that FTA indeed trains the deep fuzzy classifier DSA-FC quickly with enhanced generalization capability.

This article investigates the event-triggered fuzzy filtering issue for vehicle sideslip angle estimation with consideration of data quantization and dropouts. First, an uncertain Takagi–Sugeno fuzzy model is developed to describe vehicle nonlinear dynamics resulted from nonlinear tire dynamics, varying velocity, uncertain mass, and yaw moment inertia. Then, an adaptive event-triggered scheme is introduced between the sensor and the filter for the decision of releasing sampled data to economize limited network resource. Moreover, the network-induced constraints, such as delay, data quantization, and dropouts, are taken into account to improve the robustness of the filtering method. Based on the Lyapunov stability theory, a new event-triggered asynchronous fuzzy filtering method is proposed by establishing an augmented Lyapunov–Krasovskii functional candidate and applying integral inequalities in the derivation. Finally, simulation results are presented to verify the advantages of the proposed method in comparison with the existing results.

This paper is concerned with the human-machine shared control issue for vehicle lane keeping systems via a new fuzzy observer-based event-triggered method. In order to capture system nonlinear and uncertain characteristics such as nonlinear tire dynamics, varying velocity and driver behavioral uncertainties, Takagi-Sugeno fuzzy approach is employed to model the global driver-vehicle-road system. After system modeling, the fuzzy observer-based control structure is considered because a full states information is not available in practical driving environment. Then, most existing human-machine shared control methods are based on the periodic sampling communication mechanism. However, since the network bandwidth is limited, the above mechanism may cause oversampling and communication congestion. Thus, an adaptive event-triggered mechanism is introduced between the observer and the controller to mitigate the communication burden and improve the bandwidth utilization. Based on Lyapunov functional theory, a set of sufficient conditions are given to calculate desired human-machine shared controllers. Finally, simulation tests are implemented on Matlab/Simulink-CarSim platform and simulation results illustrate that the proposed method can achieve a favorable improvement in the lane keeping capability, the driver handling comfort and the network bandwidth utilization.

This paper studies the distributed consensus protocol for the connected vehicle platoon with heterogeneous time-varying delays and switching topologies. A third-order dynamics model with powertrain inertial lag is proposed to characterize the node longitudinal dynamics of vehicles in platoon. A novel distributed adaptive consensus protocol considering the time-varying delays and the random switched inter-vehicular communication topologies is designed to stabilize the heterogeneous vehicle platoon in the presence of external disturbance. The delay-range-dependent approach is used to deal with the system heterogeneous time-varying delays by considering the characteristics of the heterogeneous platoon. Directed graphs are adopted to describe the accessible information flow among vehicles. The necessary and sufficient conditions for the unified closed-loop vehicle platoon system are derived by using matrix analysis and Lyapunov-Krasovskii approach. Numerical simulations demonstrate the proposed method is effective.

Road traffic accidents, especially those accidents with multiple-vehicle collision usually cause injuries and mortalities. Currently, studies on collision avoidance mainly focus on the control strategies for adjacent two vehicles or multiple vehicles in a single platoon direction. This paper proposes a bi-directional collision avoidance system for multiple vehicles to minimize the collision risk under the model predictive control (MPC) framework through switching the vehicle-following mode based on the inter-vehicular states. A hierarchical structure with an upper layer and a lower layer is designed. A dual-operational mode switching strategy and the vehicle-following model are formulated in the upper layer, together with the development of the acceleration redistribution cooperative strategy for vehicle platoon. While the lower layer is designed to track the desired acceleration received from the upper layer by considering the practical situation of the control commands. To tackle complex transitional operation, a dynamic weighted tuning strategy is proposed and integrated it with the MPC. The numerical results show that the proposed system outperforms the conventional collision avoidance system and is effective to avoid a collision or minimize the total impact of the vehicle platoon when the collision is unavoidable.

This paper concerns the robust gain-scheduling control issue for autonomous path following systems with stochastic network-induced delay. Firstly, to effectively approximate the highly nonlinear tire dynamics, the linear fractional transformation formulations are employed to describe the tire cornering stiffness with a norm-bounded uncertainty. Secondly, by taking the data dropout and delay encountered in signal computation and transmission into account, a more generalized lumped delay form is proposed to unify the time-varying data dropout and network-induced delay. Moreover, a Markovian process is presented to describe the lumped delay as a stochastic distribution. Thirdly, to address the issue of varying vehicle velocity, a linear parameter varying model is established to capture vehicle lateral behaviors. Based on the stochastic stability theory, a new robust gain-scheduling path following control method is proposed for the autonomous vehicles. Finally, the experimental study is presented to bridge the gap between the theoretical and practical investigations on path following control of autonomous vehicles, and results validate the superior performance of the proposed method compared with existing works.

In this article, a novel recursive maximum correntropy-based evolving fuzzy system (RMCEFS) is proposed. The proposed system has the capability of reorganizing the structure and adapting itself in a dynamically changing environment with non-Gaussian noises. The system generates a new rule based on the correntropy criterion which represents a robust nonlinear similarity measure between two random variables and avoids recruiting the noises as the rules. Maximizing the cross-correntropy between the system output and the desired response leads to the maximum correntropy criterion for system self-adaptation. In our article, a recursive solution of the maximum correntropy criterion is derived to update the parameters of the evolving rules. This avoids the convergence problem produced by the learning size in the gradient-based learning. Also, the steady-state convergence performance of the proposed RMCEFS is studied, where the analytical solutions of the steady-state excess mean square error for the Gaussian noise and non-Gaussian noises are derived. The simulation studies show that the proposed RMCEFS using the recursive maximum correntropy converges much faster and is more accurate than the existing evolving fuzzy systems in the case of noise-free and noisy conditions.

Wind speed interval prediction plays an important role in wind power generation. In this article, a new interval construction model based on error prediction is proposed. The variational mode decomposition is used to decompose the complex wind speed time series into simplified modes. Two types of GRU models are built for wind speed prediction and error prediction. Prediction error for each mode is given a weight and accumulated to obtain the width of the prediction interval. The particle swarm optimization algorithm is applied to search for the optimal weights of the prediction errors. Experiments considering eight cases from two wind fields are conducted by using methods of interval construction in the literature for comparison with the proposed model. The result shows that the proposed model can obtain prediction intervals with higher quality.

In this paper, a correntropy-based evolving fuzzy neural system (CEFNS) is proposed for approximation of nonlinear systems. Different from the commonly used mean-square error criterion, correntropy has a strong outliers rejection ability through capturing the higher moments of the error distribution. Considering the merits of correntropy, this paper brings contributions to build evolving fuzzy neural system (EFNS) based on the correntropy concept to achieve a more stable evolution of the rule base and update of the rule parameters instead of the commonly used mean-square error criterion. The correntropy-EFNS (CEFNS) begins with an empty rule base, and all rules are evolved online based on the correntropy criterion. The consequent part parameters are tuned based on the maximum correntropy criterion, where the correntropy is used as the cost function so as to improve the non-Gaussian noise rejection ability. The steady-state convergence performance of the CEFNS is studied through the calculation of the steady-state excess mean square error (EMSE) in two cases: Gaussian noise; and non-Gaussian noise. Finally, the CEFNS is validated through a benchmark system identification problem, a Mackey-Glass time series prediction problem as well as five other real-world benchmark regression problems under both noise-free and noisy conditions. Compared with other EFNSs, the simulation results show that the proposed CEFNS produces better approximation accuracy using the least number of rules and training time and also owns superior non-Gaussian noise handling capability.

High-precision fault diagnosis is vital for widely used multistage gearbox systems. Intelligent monitoring is difficult due to the fuzzy boundaries and a variety of unseen single or simultaneous faults of such complex machinery. To solve this problem, local mean decomposition is applied to extract features effectively from the original nonstationary and nonlinear vibration signals. By exploiting the diverse functionalities of extreme learning machines (ELM) in both regression and classification, a novel dual-ELM network is proposed, in which one ELM is employed to count the number of faults and the other is used to identify the specific single- or simultaneous-fault scenarios. The proposed dual-ELM-based multilabel classifier does not rely on an empirically specified threshold. Thus, it is more self-adaptive than the existing probabilistic-based classifiers. In addition, by inheriting the advantages of the original ELM, the dual-ELMs do not require iterative fine-tuning of parameters. Finally, the training speed of the dual-ELMs is much faster than other combinations of the existing classifiers. Experimental results under various loading conditions show that the proposed dual-ELM-based fault diagnostic framework is versatile at detecting single and simultaneous faults accurately and quickly.

Recently, multilayer extreme learning machine (ML-ELM) was applied to stacked autoencoder (SAE) for representation learning. In contrast to traditional SAE, the training time of ML-ELM is significantly reduced from hours to seconds with high accuracy. However, ML-ELM suffers from several drawbacks: 1) manual tuning on the number of hidden nodes in every layer is an uncertain factor to training time and generalization; 2) random projection of input weights and bias in every layer of ML-ELM leads to suboptimal model generalization; 3) the pseudoinverse solution for output weights in every layer incurs relatively large reconstruction error; and 4) the storage and execution time for transformation matrices in representation learning are proportional to the number of hidden layers. Inspired by kernel learning, a kernel version of ML-ELM is developed, namely, multilayer kernel ELM (ML-KELM), whose contributions are: 1) elimination of manual tuning on the number of hidden nodes in every layer; 2) no random projection mechanism so as to obtain optimal model generalization; 3) exact inverse solution for output weights is guaranteed under invertible kernel matrix, resulting to smaller reconstruction error; and 4) all transformation matrices are unified into two matrices only, so that storage can be reduced and may shorten model execution time. Benchmark data sets of different sizes have been employed for the evaluation of ML-KELM. Experimental results have verified the contributions of the proposed ML-KELM. The improvement in accuracy over benchmark data sets is up to 7%.

Air-ratio is an important engine parameter which relates closely to engine emissions, power, and brake-specific fuel consumption. Model predictive controller (MPC) is a well-known technique for air-ratio control. This paper utilizes two advanced techniques, discrete wavelet transformation (DWT) and relevance vector machine (RVM), to develop wavelet relevance vector machine model predictive controller (W-MPC) for air-ratio regulation. To compensate for the modelling error of W-MPC and system disturbances, the W-MPC is proposed to connect in parallel with a proportional-integral (PI) controller so as to form a new hybrid model predictive controller (H-MPC). The proposed H-MPC is implemented on a real engine to evaluate its effectiveness. Its control performance is also compared with the W-MPC without PI controller and the latest MPC for engine air-ratio control in the literature. Experimental results show the superiority of the proposed H-MPC over the other two controllers, which can more effectively regulate the air-ratio to target values under external disturbance. Therefore, the proposed H-MPC is a promising scheme for engine air-ratio control.

Extreme learning machine (ELM) has become a popular topic in machine learning in recent years. ELM is a new kind of single-hidden layer feedforward neural network with an extremely low computational cost. ELM, however, has two evident drawbacks: 1) the output weights solved by Moore-Penrose generalized inverse is a least squares minimization issue, which easily suffers from overfitting and 2) the accuracy of ELM is drastically sensitive to the number of hidden neurons so that a large model is usually generated. This brief presents a sparse Bayesian approach for learning the output weights of ELM in classification. The new model, called Sparse Bayesian ELM (SBELM), can resolve these two drawbacks by estimating the marginal likelihood of network outputs and automatically pruning most of the redundant hidden neurons during learning phase, which results in an accurate and compact model. The proposed SBELM is evaluated on wide types of benchmark classification problems, which verifies that the accuracy of SBELM model is relatively insensitive to the number of hidden neurons; and hence a much more compact model is always produced as compared with other state-of-the-art neural network classifiers.

Fuel efficiency and pollution reduction relate closely to air-ratio (i.e. lambda) among all of the automotive engine control variables. Accurate lambda prediction is essential for effective lambda control. This paper presents an online sequential algorithm for relevance vector machine (RVM) to build a time-dependent RVM lambda function which can be continually updated whenever a sample is added to, or removed from, the training dataset. In order to evaluate the effectiveness of the online sequential algorithm, three lambda time series obtained from experiments under different engine operating conditions were employed. The prediction results under the online sequential algorithm over unseen cases were compared with those under decremental least-squares support vector machine. From the experiments, the online sequential RVM shows promising results and is superior to the typical online algorithm.