Graph neural networks are increasingly applied to multimodal medical diagnosis for their inherent relational modeling capabilities. However, their efficacy is often compromised by the prevailing reliance on a single, static graph built from indiscriminate features, hindering the ability to model patient-specific pathological relationships. To this end, the proposed Multi-Activation Plane Interaction Graph Neural Network (MAPI-GNN) reconstructs this single-graph paradigm by learning a multifaceted graph profile from semantically disentangled feature subspaces. The framework first uncovers latent graph-aware patterns via a multi-dimensional discriminator; these patterns then guide the dynamic construction of a stack of activation graphs; and this multifaceted profile is finally aggregated and contextualized by a relational fusion engine for a robust diagnosis. Extensive experiments on two diverse tasks, comprising over 1300 patient samples, demonstrate that MAPI-GNN significantly outperforms state-of-the-art methods.

As an important component of clean energy, wind power generation is of great significance in promoting energy structure transformation and achieving sustainable development. It is particularly crucial to develop precise and effective fault diagnosis technology to ensure the safe and stable operation of wind turbines. This paper proposes a fault diagnosis method for wind power transmission systems based on model and data fusion, called PINN_Transformer. The method integrates the nonlinear dynamics model of the planetary gearbox as physical prior knowledge into a Transformer-based diagnostic network. To achieve this fusion, a novel physics-informed loss function is constructed, which maps the system’s vibration differential equations to the time-frequency domain via wavelet transform, and simultaneously incorporates constraints based on energy conservation and time-frequency feature matching. This approach embeds the governing physical laws directly into the learning process of the deep network, addressing the interpretability gap in purely data-driven methods while enhancing feature discrimination. Experimental results demonstrate significant advantages of PINN_Transformer compared to other advanced diagnostic methods, achieving a fault diagnosis accuracy of 99.84%. Furthermore, the model maintains robust performance with an accuracy above 97.07% under additive noise conditions, confirming its good engineering application value.

The repetitiveness prerequisite of iterative learning control has always been the main obstacle to promoting its practical applications. In this article, a novel adaptive iterative learning reliable control scheme is proposed for the nonrepetitive systems with multiple iteration-varying parametric uncertainties, where actuator faults and state delays are considered simultaneously. During the design of the controller, the class- $k_{\infty } $ function is leveraged to dispose of the unmodeled lumps of systems through neural networks, and the transformation of control signals is established to compensate for the negative impact of the inefficient actuator. The technical features of our approach lie in an innovative parametric estimation mechanism that integrates the hyperbolic tangent function and an auxiliary sequence is presented to accommodate the nonrepetitive uncertainties, thus achieving the zero-error convergence of output. As the main merits, the proposed control scheme is promising to manifest better performance and practicality than the existing methods, owing to the weak assumptions on the system dynamics, the little prior knowledge of parametric uncertainties, and the strong learning ability of the controller.

The periodic operation pattern of high-speed train (HST) grants the immense potential for iterative learning control (ILC) approach regulating the displacement and velocity, but the non-repetitive uncertainties caused by carrying loads, random disturbances, etc., may weaken the capability of controller. Further, the typical operating situations of rail transit, e.g., station entrance/exit, slowdown sections, can compress the safety margin of HST, increasing the difficulty of precise tracking. In this paper, an adaptive ILC scheme is proposed for HST subject to the safety constraints, where the unknown iteration-varying parameters and the modeling inaccuracies are handled deliberately. Our technical route could be divided into two phases. The transformation mechanism of tracking errors, that can convert the control problem of constrained systems into an unconstrained form, is first established to guarantee that HST is always located within the safety zone. On this basis, the iterative learning controller is devised through integrating the hyperbolic tangent function and iteration-related sequence, where the neural network is leveraged to approximate the unmodeled lumps. The main innovative features lie in that, the iteration-dependent terms of control system are evolved into the parametric compensation components of controller and the iterative convergence parts, while the nested structure of control law is built to accommodate the iteration-variation of loads. As a result, the proposed approach can theoretically achieve the zero-error tracking of HST in the presence of the non-repetitive uncertainties and safety constraints, which indicates the better performance and practicability than the existing ones.

This study investigates the high-order internal model (HOIM) based data-driven iterative learning control of HSRs subject to faded channels. Firstly, the nonlinear train dynamics are converted into an input/output data-based model by using a linearization approach. Then, the HOIM of the desired speed trajectories is introduced and the fading channel is used to model the unreliable transmission network. Next, the model free adaptive iterative learning control (MFAILC) strategy is implemented based on the train input and faded output information, and the theoretical convergence analysis of the speed error is carried out. Eventually, the validity of the MFAILC scheme is checked in simulation by applying the CRH-380 HSRs on a StarSim hardware-in-loop semi-physical platform.

The coordination of multiple high-speed trains (MHSTs) is considered an effective means to enhance train tracking accuracy and operational efficiency. In this study, the model free adaptive control (MFAC) of MHSTs under false data injection attacks (FDIAs) and input limits is investigated within the framework of data-driven control. The advantage of this control scheme lies in its ability to mitigate performance degradation caused by model inaccuracies. Firstly, a dynamic model for MHSTs is established and then transformed into an equivalent linearized form that solely relies on input and output (I/O) data. Secondly, considering power limitations in the traction network and external FDIAs during direct train-to-train (T2T) communication, a data-driven coordinated MFAC scheme for MHSTs is developed. Finally, the effectiveness of the controller, coordination performance among MHSTs, as well as the impact of external constraints on MHSTs are verified through numerical simulations.

Torque ripples and disturbances pose significant obstacles to achieving superior speed regulation performance of the permanent magnet synchronous motor (PMSM). This study proposes an enhanced sliding mode control (SMC) approach to further elevate the dynamic responsiveness and antidisturbance ability of the PMSM. First, an advanced fast reaching law (AFRL), which introduces system errors into the power and exponential terms, is proposed to simultaneously reduce the reaching time and sliding mode chattering. A modified sliding mode observer (MSMO) is then constructed to assess the variation of the load torques, and an iterative learning law is designed to learn the periodic disturbances. The integration of the MSMO and iterative learning law forms an iterative composite compensation strategy, which effectively elevates the observation accuracy of system disturbances and strengthen the system’s robustness. The enhanced sliding controller is consequently developed according to the AFRL and the iterative composite compensation. The stability of the AFRL and the closed-loop PMSM system, as well as the convergence of tracking errors, are rigorously substantiated using the Lyapunov theory. Experimental results reveal that the proposed controller exhibits smaller torque ripples, faster convergence speed, reduced chattering, and considerable antidisturbance capability.

Cooperative control of multiple high-speed trains (MHSTs) is considered as a pivotal technology for enhancing the safety and efficiency of train groups. This study investigates the problem of distributed iterative learning control for MHSTs under the input saturation, employing a data-driven control strategy. Moreover, a novel independent weights-based communication protocol is developed to improve the coordination efficiency of MHSTs. Firstly, a novel linearization method is utilized to transform the dynamic model of MHSTs into an equivalent linearized model associated with saturated inputs. Secondly, based on this model, we develop both a train-to-train (T2T) communication protocol and a distributed model free adaptive iterative learning control (DMFAILC) scheme that are independent of any specific models or structural information about MHSTs. Subsequently, the overall stability is analyzed using the compression mapping method, and the complete tracking of HSTs and the coordination performance of MHSTs are confirmed through Simulink simulations and real-time StarSim hardware-in-the-loop (HIL) semi-physical platforms. Note to Practitioners—The practical challenges that drive this research on cooperative control of MHSTs are the intricate nature of train models and the inherent instability in train operating conditions. Moreover, potential applications include automatic operation of HSTs and coordination of MHSTs. Specifically, the contributions of this work include: (1) eliminating the need for precise models of HSTs; (2) establishing stability conditions for HSTs under saturation conditions; and (3) enhancing coordination efficiency among MHSTs through an independent weight protocol. However, a limitation of this study is that the theoretical findings have not been validated on real HSTs. To address the current lack of practical implementation of the train cooperative control strategy, further investigations will be conducted to incorporate more realistic constraints, such as those related to traction network limitations and optimal scheduling considerations.

This article investigates the fixed-time distributed average tracking (DAT) problem for nonlinear multiagent systems with unity relative degree under external disturbances. A distributed control framework is developed to guarantee fixed-time convergence of all agents' outputs to the target trajectory, which is defined as the average of multiple nonlinear reference signals. The approach consists of three main components. First, a steady-state generator is introduced to reconstruct the desired trajectory. Using this generator, a distributed observer is designed to estimate the target trajectory while ensuring robustness against initialization errors. Subsequently, an observer-based output-feedback controller is developed to guarantee the convergence of each agent's output to its corresponding reference signal within a fixed time. Through rigorous theoretical analysis, it is proved that the proposed control architecture ensures fixed-time convergence to the target trajectory, effectively solving the fixed-time DAT problem. The effectiveness of the proposed method is validated through numerical simulations.

To address the challenge of secure federated modeling in fault diagnosis under imbalanced data scenarios for multi-railway high-speed train bogies, this study proposes a multi-rank federated distillation (MFD) framework aimed at enhancing the generalization capacity of clients with limited sample sizes. First, the MFD framework is designed to perform multiple distillation tasks, with each task’s loss function decoupled into two components to balance losses between target and non-target classes. Second, an adaptive weight adjustment strategy is introduced to efficiently train models by coordinating the loss outputs across these tasks. Third, to mitigate the learning costs associated with the MFD, clients share a foundational shallow network via model transfer while incorporating personalized modules to improve adaptability. By validating the proposed framework on datasets from high-speed train bogies across multiple railways, this study demonstrates its effectiveness in addressing challenges associated with secure federated modeling while maintaining satisfactory diagnostic performance. The findings present a viable solution for implementing federated learning among clients with imbalanced data in industrial applications.

A novel iterative learning control (ILC) strategy is developed for displacement and velocity tracking control of high-speed trains (HSTs) across all operational phases. In practical operations, HSTs encounter complex nonlinear uncertainties, such as variations in coupler forces and aerodynamic resistance, which are more appropriately characterized by norm-bounded models rather than traditional Lipschitz continuous disturbances. To capture these effects accurately, a multi-particle dynamic model of HSTs with norm-bounded uncertainties is formulated, considering the coupler dynamics, mechanical resistance, and aerodynamic resistance acting upon different carriages. Based on this model, a robust ILC scheme, together with an associated parameter updating law, is designed to ensure precise tracking control despite the presence of nonlinear uncertainties. Furthermore, the classical resetting condition in conventional ILC frameworks is replaced by a practical alignment condition that better reflects the continuous operation characteristics of HSTs. A composite energy function (CEF) is constructed to rigorously prove the convergence of control errors. Real-time hardware-in-the-loop (HIL) simulations are conducted to validate the effectiveness of the proposed method. The proposed strategy achieves effective tracking control and stability across traction, cruising, coasting, and full braking stages.

In the context of high-speed trains (HST) bogie fault diagnosis, most existing state-of-the-art approaches struggle to effectively identify engineering fault types that lack historical records, leading to issues such as insufficient feature learning and high misdiagnosis rates. To tackle the challenges, this article introduces a generalized zero-shot learning (GZSL) strategy and presents a fault diagnosis framework for HST bogies, referred to as “ResDDPM-GZSL.” The study initially designs and constructs a foundational attribute description matrix for HST bogies. Residual networks are utilized to extract data features, which facilitates the bidirectional mapping among data, attributes, and features. Furthermore, the structure of the diffusion model is enhanced and customized for better adaptation to low-dimensional data, thereby improving the capability of the model to efficiently learn and generate latent features of unknown data, while maintaining stability. Finally, the model is established based on known data feature extraction and unknown data feature generation. Experimental results demonstrate that the average diagnostic accuracy for known fault classes exceeds 95%, while the average diagnostic accuracy for unknown fault classes surpasses 70%, with a harmonic mean diagnostic accuracy exceeding 80%. The results obtained significantly surpass those of other generative method-based diagnostic approaches, indicating that the study offers an effective solution for zero-shot learning fault diagnosis.

Automation of abrasive machining operations (AMO) has become a challenging aspect in the remanufacturing industry where it is required to conduct operations on a surface of which the exact dimensions are unknown. In such cases, skilled human workers have to step in to perform labor-intensive tasks with inconsistent quality. In existing research work, collaborative robots are used to partially automate such operations under human supervision. However, these methods do not perform learning and control simultaneously and are often affected by the interactions of the human operator. In this paper, a novel learning and control scheme is proposed where the robot explores an unknown surface iteratively while achieving the desired contact control performance under supervision and occasional interference from the human operator. The unknown surface is divided into sub-regions, and the learning and control parameters are updated each time the robot visits each sub-region. This method is independent of the path of the robot and thus is unaffected by the irregularities introduced by a human operator's interactions. The proposed method is applied to force control, stiffness learning, and orientation adaptation cases. The validity of this method is shown via simulations as well as experiments conducted using a Kinova Gen3 7-DOF robot.

The paper studies the faded communication-based coordinated model-free adaptive iterative learning control (MFAILC) of multiple high-speed trains (MHSTs) against periodic denial-of-service (PDoS) attacks. First, considering the nonlinearity and uncertainty of the train operation, the dynamic model of MHSTs is constructed, and then followed by the newly established linear data-relationship model. Next, the random faded channel is expressed by Rice fading model, and the PDoS attacks are introduced with the help of the random coefficients. After giving the theoretical analysis, the compensation scheme is conducted, and the research is further extended to the switching topologies. Finally, a set of numerical tests is conducted to confirm the practicability of the MFAILC approaches.Note to Practitioners—HSTs have the characteristics of high speed, high safety, etc. The practical problems that motivate this work are the complexity of train model, the instability of the networks and the urgent requirement to further improve the operation efficiency. Meanwhile, the possible application areas include the automatic operation of HSTs and the cooperative operation of train groups. Specifically, the potential of this work includes: 1) eliminating the requirement of detailed modeling of train dynamics; 2) providing a theoretical basis for reliable train operation in an unstable network environment, and 3) improving the efficiency of train group operation through cooperation. Nevertheless, the limitation of this paper is that the results have not been verified on the actual trains and railways. To extend it to be more practical, we will further investigate more practical constraints in the train operation environment, such as the constraints of the traction network, the constraints of the track adhesion condition, and also continue to optimize the controller parameters iteratively.

In this paper, the distributed cooperative control of virtual coupling high-speed trains (HSTs) subject to full-state constraints, actuator limitations, dynamical uncertainties and environmental disturbances is investigated. Targeting at the full-state constraints in cooperative operation of HSTs, a distributed nonlinear state-dependent function (DNSDF) is first proposed to convert the state-constrained problem of the leader-following consensus control to the boundedness problem of DNSDF. Then, the distributed control law of each train is designed by combining the command filtering backstepping method and the adaptive neural network approximation technique. Meanwhile, combined with the DNSDF, a novel auxiliary dynamical system (ADS) is designed to compensate for the adverse effects of actuator input saturation, and thus ensure the closed-loop stability of the HSTs system when the state constraints and the input saturation are considered simultaneously. By utilizing the Lyapunov theory, the convergence of the proposed controller is analyzed. Finally, the feasibility and effectiveness of the proposed control scheme are verified by simulations.Note to Practitioners—This work was motivated by the problem of cooperative control for virtual coupling HSTs with different initial states, actuator input saturation, full-state constraints, etc. The proposed approach addresses the train position and speed constraints by applying DNSDF, which can ensure train coordinated operation with relative braking distance and further reduce the tracking interval between trains. Specifically, the upper bound of the train position constraint varies with the real-time position of the preceding train and the relative speed of the adjacent trains, rather than a constant value. More importantly, an ADS is designed based on the DNSDF, which guarantees the stability of the controller when the input saturation and state constraints exist simultaneously, and avoids the chattering phenomenon of the train control input. The simulation results show that the trains can operate cooperatively at any initial speed within the speed limitations. In future, we will focus on the cooperative control of HSTs with communication delay, and the energy saving optimization cooperative control of HSTs.

The coordination of multiple high-speed trains (MHSTs) can improve the transportation efficiency and the safety performance. However, the complicated dynamic characteristics of MHSTs and the unreliable train-to-train (T2T) (wireless) communication modes are challenging the conventional control approaches. Focusing on the adverse impact from denial-of-service (DoS) attacks and faded channels caused by the T2T networks, the study designs a distributed adaptive iterative learning controller (DAILC) with recovery and compensation mechanisms, which is a model-free approach. Relying on the novel equivalent linearization strategy, a DAILC is established by using the distributed tracking errors, and the theoretical analysis has verified the complete tracking performance of MHSTs. The results in simulation test demonstrate the feasibility of the proposed DAILC and the effectiveness of the recovery and compensation mechanisms.

Deep Reinforcement Learning (DRL) is the most promising technology for improving high-speed train’s energy efficiency and operation quality. Existing solutions, however, suffer from three significant limitations: 1) They cannot effectively constrain the huge exploration space generated by high-speed trains under high temporal deformability and long-distance trips; 2) The reward function has no adaptability to the different energy-efficiency difficulties of different travel schedules, and the agent will receive incorrect reward signals, requiring manual adjustment; 3) They do not avoid the invalid action sequences of the agent well. To address this challenge, we propose a revolutionary Boundary Constrained and Pre-evaluated Reinforcement Learning (BCPRL) approach to alleviate these issues. This approach combines the Shrink Trajectory Exploration Space (STES) module, the Pre-evaluated Energy-efficiency Scenario Complexity (PESC) module, and the Twin Delayed Deep Deterministic Policy Gradient (TD3) module and uses a hybrid of STES and TD3 to make train operation decision-making to improve the operation quality and learning efficiency of the agent. Numerical experiments validate the effectiveness of the BCPRL approach, which, by drastically reducing the exploration space and getting the agent the correct reward signal, not only maintains excellence in efficiency and punctuality but also far surpasses the other baseline approaches in learning efficiency and robustness.

Due to device operating environment limitations and data privacy protection, it is frequently difficult to obtain sufficient high-quality labeled data from devices, resulting in an insufficient generalization ability of fault diagnosis model. Therefore, a high-performance federated learning framework is proposed in this work, which makes improvements in the procedure of model aggregation and local model training. In the model aggregation of central server, an optimization aggregation strategy in which forgetting Kalman filter (FKF) is combined with cubic exponential smoothing (CES) is proposed to improve the efficiency of federated learning. In the local model training of multiclient, a deep learning network combined with multiscale convolution, attention mechanism, and multistage residual connection is proposed, which is able to fully extract multiclient data features simultaneously. Meanwhile, experiments on two machinery fault datasets show that the proposed framework is capable of achieving high accuracy and strong generalization of fault diagnosis on the premise of protecting data privacy in actual industrial situations.

Contact tooling operations like sanding and polishing have been high in demand for robotics and automation, as manual operations are labour-intensive with inconsistent quality. However, automating these operations remains a challenge since they are highly dependent on prior knowledge about the geometry of the workpiece. While several methods have been developed in existing research to automate the geometry learning process and adjust the contact force, human supervision is heavily required in the calibration of workpieces and the path planning of robot motion in such methods. Furthermore, the stiffness identification of the workpiece is not considered in most of these methods. This paper presents a human-robot collaboration (HRC) framework, which is able to perform surface exploration on an unknown object combining the operator's flexibility with the control precision of the robot. The operator moves the robot along the surface of the target object, and the robot recognizes the surface geometry and surface stiffness while exerting a desired contact force through control. For this purpose, a mesh iterative learning control (MILC) is developed to learn the surface stiffness, plan the exploration path, and adjust contact force through repetitive online correction based on HRC. The proof of learning convergence and the results of the simulation and experiments performed using a 7-DOF Sawyer robot demonstrate the validity of the proposed controller.

A popular path learning method is to use off-line programming by demonstration (PbD) to plan a rough path, but it is subjected to uncertainties in the environment so needs to be updated during the task execution. For this purpose, a spatial iterative learning control (sILC) is developed to learn an accurate path through intuitive online correction based on human-robot interaction (HRI). To improve the efficiency and accuracy of the path learning, a visual assistance system is added to HRI, which helps the robot to find the initial path point and complement the correction of the learning error. This method mitigates the requirement on classic ILC that the time period should be consistent in the repetitive interaction task and utilizes the complementary advantages of vision and force sensing, thus addressing the limitations of the vision-based or HRI methods. The rigorous proof of learning convergence and the results of the simulation and experiments on a 7-degree-of-freedom (DoF) Sawyer robot platform illustrate the significance and advantages of the proposed method.Note to Practitioners—The problem of accurate path learning of robotic manipulators is addressed in this paper, which is found in ample applications such as welding and laser cutting. When the required path is irregular, it is difficult to define it based on offline programming and calibration. This paper presents a new human-robot interactive learning framework, in which the interaction force and machine vision are combined with sILC to achieve online detection and correction for learning and tracking an unknown path. This framework leads to an intuitive human-robot collaboration system where the human operator can fine tune the robot’s motion through direct physical interaction, and at the same time the robot improves its tracking performance automatically based on visual servoing.

This paper studies the distributed data-driven event-triggered model free adaptive iterative learning control (ETMFAILC) of multiple high-speed trains (MHSTs) under iteration-varying topologies, which breaks away from the dependence on the train dynamics. Firstly, the nonlinear MHSTs with unknown dynamics are converted into a linear model. Then, combining the proposed event-based triggering condition and the linear model, the ETMFAILC scheme under the fixed topology is designed. Next, theoretical analysis proves the bounded input bounded output (BIBO) stability of MHSTs. Finally, the study is extended to the switching topologies and the validity of the ETMFAILC is verified by a numerical example.

In this article, an adaptive iterative learning control scheme is presented for a class of nonlinear parametric strict-feedback systems with unknown state delays, aiming to achieve the point-wise tracking of desired trajectory in a finite interval. The appropriate Lyapunov-Krasovskii functions are established to compensate the influence of time-delay uncertainties on the control systems. As the main features, the proposed approach integrates the command filter into the backstepping procedure to avoid the differential explosion problem that may occur with the increase of system order, and introduces the hyperbolic tangent functions into the learning controller to handle the singularity problem thus maintaining the continuity of input signal. The results of theoretical analysis and numerical simulation demonstrate that the tracking errors at the entire period will converge to a compact set along the iteration axis. Compared with the existing works, the proposed control scheme is promising to manifest the better performance and practicability owing to the learning mechanism, the dynamic model, as well as the implementation of controller.

This article considers the speed tracking control problem for high-speed train systems (HSTs) under the condition of passing through neutral sections in the presence of parametric uncertainties. Noticing the prominent feature of HSTs operation, i.e., the spatial repetitiveness, a novel spatial iterative learning control (ILC) scheme is proposed. First, the motion dynamic model of HSTs is constructed with the aid of temporal-spatial conversion. Meanwhile, input saturation constraint is introduced to address the limitation of system power supply capability and the loss of traction/braking force in neutral section. Then, the ILC law and the associated parametric updating law are devised to address the system uncertainties and realize the adaptive tracking control simultaneously. The stability of the closed-loop system and the convergence of the tracking errors are confirmed based on a space-weighted Lyapunov–Krasovskii-like composite energy function (CEF). Finally, numerical simulations are performed to illustrate the effectiveness of the proposed control scheme.

In this article, a novel iterative learning control scheme is proposed for high-speed trains, aiming to track the desired reference displacement and velocity, where the Krasovskii function is constructed to compensate for the negative influence of unknown time-varying speed delays. The main feature of the proposed approach is that the hyperbolic tangent function and the command filter are integrated into the learning controller to overcome the singularity problem that may occur during the control process and relax the requirement for the derivability of the desired velocity. The stability of control system is strictly proved through establishing the composite energy function, and the effectiveness is confirmed via numerical simulations. Compared with the existing works, the merits of the proposed control scheme lie in that more general nonlinear uncertainties are imposed on the dynamic model of train instead of the Lipschitz condition, and the reference acceleration assigned by the railway department is not required.Note to Practitioners—High-speed train always runs periodically on the same railway, e.g., the same tunnels, slopes, and bridges, according to the scheduling plans developed by the railway department. Due to the repetitive operation pattern, the iterative learning control has the prospect of becoming an inherent method for devising the tracking controller of trains. Nevertheless, the unknown speed delays, which are inevitable due to the damping effect of wheel rails, couplers, and so on as well as the disturbance of external environments, may degrade the performance of control system and even cause instability in severe cases. As a result, this article exploits a compensation method to eliminate the effects of unknown delay under the iterative learning control framework, thus guaranteeing the safety of train operation and the comfort of passengers. To enhance the practicability, the hyperbolic tangent function is introduced to keep the continuity of control signal, and the command filter is synthesized to reduce the complexity of controller implementation. Although the stability analysis and numerical simulations have confirmed the feasibility and effectiveness of the proposed scheme, it is still expected to be verified by experiments in the future.

In this article, an iterative-learning-based robotic controller is developed, which aims at providing a prescribed assistance or resistance force to the human user. In the proposed controller, the characteristic parameter of the human upper limb movement is first learned by the robot using the measurable interaction force, a recursive least square (RLS)-based estimator, and the Adam optimization method. Then, the desired trajectory of the robot can be obtained, tracking which the robot can supply the human’s upper limb with a prescribed interaction force. Using this controller, the robot automatically adjusts its reference trajectory to embrace the differences between different human users with diverse degrees of upper limb movement characteristics. By designing a performance index in the form of interaction force integral, potential adverse effects caused by the time-related uncertainty during the learning process can be addressed. The experimental results demonstrate the effectiveness of the proposed method in supplying the prescribed interaction force to the human user. Note to Practitioners—This article concentrates on developing a novel control technique to make the robot supply a prescribed interaction force to the human user in the presence of time-related uncertainties. The proposed control method is applicable to various scenarios of the human–robot interaction, e.g., it can be used for rehabilitation robots to provide assistive or resistive force to stroke patients or for exoskeleton robots to provide assistive force to human users for completing heavy-load tasks. Moreover, the desired interaction force can be tailored for different human users according to their needs and different task objectives. Consequently, the proposed controller can serve diverse users and has a promising perspective in automation.

A spatial iterative learning control (sILC) method is proposed for a robot to learn a desired path in an unknown environment. When interacting with the environment, the robot initially starts with a predefined trajectory so an interaction force is generated. By assuming that the environment is subjected to fixed spatial constraints, a learning law is proposed to update the robot's reference trajectory so that a desired interaction force is achieved. Different from existing iterative learning control methods in the literature, this method does not require repeating the interaction with the environment in time, which relaxes the assumption of the environment and thus addresses the limits of the existing methods. With the rigorous convergence analysis, simulation and experimental results in two applications of surface exploration and teaching by demonstration illustrate the significance and feasibility of the proposed method.

Fault diagnosis of high-speed train (HST) bogie plays an indispensable role in guaranteeing the safety and stability of the daily operation of HST. Up to now, the well-established fault diagnosis models of HST bogie, which are usually trained by supervised learning mechanism, require that the training and testing data satisfy the same probability distribution. Consequently, those methods could lose their efficacy when the probability distribution of the testing data is changed owing to the variation of HST running speed and the labeled data corresponding to the changed speed is absent. To address this, a stepwise adaptive convolutional network (SACN) is proposed to learn the domain-invariant features of vibration data in different speed domains. Moreover, a novel in-and-out stepwise transfer method is designed to deal with the scenario of continuous change in vehicle speed. The experimental tests of the proposed method are conducted using the dataset acquired by SIMPACK via the HST model CRH380 A, mainly addressing the single and compound failure classification problem of the three key components of HST bogie, namely, the air spring, antiyaw damper, and lateral damper. Overall, the proposed SACN achieves an average accuracy of 96.1%, demonstrating the remarkable performance of domain adaptation in performing fault diagnosis of HST bogie under variant running speeds.

The precise operation control of high-speed trains is pivotal to maintain the safety and efficiency of trains, while the inevitable state delays will seriously attenuate the performance of control system. In this paper, an adaptive iterative learning control (ILC) approach for high-speed trains is presented in the presence of the nonlinearly parameterized uncertainties and multiple unknown state delays, aiming to drive that the displacements and velocities of trains can track the desired reference trajectories. To describe the operational dynamics of trains more realistically, the multi-particle model of trains involving multiple time-varying delays is established by analyzing the aerodynamic resistance, mechanical resistance, and coupler force acting on different cars. The proposed adaptive ILC scheme fully leverages various techniques, e.g., the hyperbolic tangent function, the parameter separation, to cope with the inherent nonlinearities, uncertainties and couplings of system. Specially, to eliminate the negative influence of unknown delays, an appropriate Krasovskii function is integrated into the Lyapunov criterion to devise the learning controller and check the stability of control systems. The novelties of our work lie in that the refinement model and periodical characteristic are simultaneously utilized to improve the practicability and performance of control scheme for the high-speed trains with multiple state delays.

Nowadays, precise train parking has become a key technology of automatic train operation. Due to the high nonlinearities and various uncertainties existing in the dynamics of urban rail trains (URTs), it is challenging to develop an effective parking controller to achieve high-precision parking. To address this issue, a novel robust adaptive backstepping controller is proposed in the paper, where a robust term is employed to compensate for the system uncertainties caused by the brake shoe, and meanwhile several parametric adaption laws are equipped to estimate the uncertain system parameters as well as the external disturbances. The closed-loop stability of the controlled system is analyzed rigorously by virtue of the Lyapunov theory, and the effectiveness of the proposed control scheme in precise parking of URTs is demonstrated through numerical simulations.

The lateral vibration of high-speed train reduces the ride stability and passenger comfort. Semi-active suspension system is often adopted to suppress the lateral vibration of trains due to its low cost and low energy consumption in control, where magnetorheological (MR) damper is the main vibration absorber. In this paper, a full model of the controlled system that consists of the 3-degree of freedom train model and the hysteretic MR damper model is first built. Then, a second-order sliding mode (SOSM) controller is designed for the suppression of lateral vibration of train, where the hysteresis and non-hysteresis nonlinearities are addressed simultaneously and rigorously. Finally, comparative simulations are conducted under the excitation of the German low-interference track spectrum. The results show that the proposed controller can suppress the lateral vibration of high-speed train efficiently in the sense that, compared with the passive control, the internal model-based resonant control and repetitive learning control, the suspension ratio of root-mean-square of lateral acceleration is reduced by 96.98%, 35.70% and 10.54%, respectively.

This paper studies the dissipative control problem of the multibody high-speed train (HST) systems with nonuniform sampling mechanisms and logarithmic quantizers, in which the transmitted signals are subject to random fading phenomenon. The tracking error dynamic model of HST is firstly established and the logarithmic quantizers for both the input and output (I/O) signals are designed. The faded I/O signals are described by the Rice fading model, in which the mathematical expectation and variance are given in advance. Then, based on the Lyapunov-Krasovskii functional approach with the consideration of time-varying delay, sufficient conditions are derived to ensure the convergence of tracking error and that HST is strictly dissipative. Further, the design method of the gain matrix is obtained by employing the linear matrix inequalities (LMI) techniques and a compensation algorithm is designed to offset the adverse effect brought by the fading measurements. Finally, the effectiveness of the proposed controller is verified by a numerical example from Japan Shinkansen HST.

This article investigates human-driven robots via physical interaction, which is enhanced by integrating the human partner’s motion intention. A human motor control model is employed to estimate the human partner’s motion intention. A system observer is developed to estimate the human’s control input in this model, so that force sensing is not required. A robot controller is developed to incorporate the estimated human’s motion intention, which makes the robot proactively follow the human partner’s movements. Simulations and experiments on a physical robot are carried out to demonstrate the properties of our proposed controller.

This paper presents a novel method for learning and tracking of the desired path of the human partner in physical human-robot interaction. Combining the Adam optimization algorithm with iteration learning control (ILC), a path learning method is designed to generate and update reference waypoints according to the human partner’s desired path. This method firstly uses the Adam optimization algorithm to update the robot’s reference waypoints in an online manner. Then, an ILC is developed to further modify the waypoints and reduce the difference between the robot’s actual path and the human partner’s desired path in an iterative manner. Simulations and experiments on a 7-DOF Sawyer robot are carried out to show the effectiveness of our proposed method.

The precise tracking control of high-speed train is an essential prerequisite to ensure the safety and comfort of the train. In this paper, an adaptive iterative learning control (ILC) scheme for the velocity and displacement tracking of high-speed train is proposed to handle the unknown time-varying parameters and lumped uncertainties. The composite energy function (CEF) method is used to analyze the stability of closed-loop system. Since the train usually runs on the same railway periodically, such as the same tunnels, slopes, bridges, etc., ILC is an inherent method for designing the tracking controller that is able to improve the operation performance of train iteratively. To the best of our knowledge, it is the first time that the multi-agent framework and ILC methodology are considered simultaneously in a single train, which can better reveal the coupled characteristic of adjacent cars and impose the repetitive operation pattern of train. The results of numerical simulations show that the tracking performance of the train toward the reference trajectory is significantly improved along with the increase of the number of operations.

This article presents a novel perspective to improve the ride quality of high-speed trains (HSTs), namely, by virtue of the periodicity of lateral dynamics to suppress the lateral vibration of HST. To resolve the contradiction between the complex HST model and the effective controller design, a simplified three-degrees-of-freedom (3-DOF) quarter-vehicle model is first employed for controller design, while a 17-DOF full-vehicle model is built for efficiency verification, where periodic and random track irregularities are considered, respectively. An active repetitive learning control (RLC) method is proposed to achieve the periodic tracking control, where the learning convergence is proved rigorously in a Lyapunov way. The configuration of RLC-based lateral suspensions is economical in the sense that only four actuators and six sensors are needed. It is verified by simulation that, compared with the dynamic matrix controller, the proposed RLC controller has greatly reduced the lateral vibration of a vehicle body, especially the lateral acceleration in the frequency range of (0, 3] Hz to which human body is strongly sensitive.

As an important part of high-speed train (HST), the mechanical performance of bogies imposes a direct impact on the safety and reliability of HST. It is a fact that, regardless of the potential mechanical performance degradation status, most existing fault diagnosis methods focus only on the identification of bogie fault types. However, for application scenarios such as auxiliary maintenance, identifying the performance degradation of bogie is critical in determining a particular maintenance strategy. In this article, by considering the intrinsic link between fault type and performance degradation of bogie, a novel multiple convolutional recurrent neural network (M-CRNN) that consists of two CRNN frameworks is proposed for simultaneous diagnosis of fault type and performance degradation state. Specifically, the CRNN framework 1 is designed to detect the fault types of the bogie. Meanwhile, CRNN framework 2, which is formed by CRNN Framework 1 and an RNN module, is adopted to further extract the features of fault performance degradation. It is worth highlighting that M-CRNN extends the structure of traditional neural networks and makes full use of the temporal correlation of performance degradation and model fault types. The effectiveness of the proposed M-CRNN algorithm is tested via the HST model CRH380A at different running speeds, including 160, 200, and 220 km/h. The overall accuracy of M-CRNN, i.e., the product of the accuracies for identifying the fault types and evaluating the fault performance degradation, is beyond 94.6% in all cases. This clearly demonstrates the potential applicability of the proposed method for multiple fault diagnosis tasks of HST bogie system.

Fault diagnosis of high-speed train (HST) bogie is essential in guaranteeing the normal daily operation of an HST. In prior works, feature extraction from multisensor vibration signals mainly relies on signal processing methods, which is independent of the classification process. Based on convolutional neural networks (CNNs), this paper presents a novel fault diagnosis system using the residual-squeeze net (RSNet), which is directly applicable to raw data (time sequences) and does not require any signal transformation or postprocessing. In this network, information fusion is achieved by using the convolutional layer. More specifically, via the squeeze operation, an optimal combination of channels is learnt by training the network. Experimental results obtained by using SIMPACK simulation data demonstrate the effectiveness of the proposed approach in both complete failure case and single failure case, with diagnosis accuracy near 100%. The proposed approach also shows good performance in identifying the locations of faulty components. Comparisons between RSNet and competitive methods shows the advantages of RSNet for fault classification.

This paper addresses the vibration control and the input constraint for an Euler-Bernoulli beam system under aperiodic distributed disturbance and aperiodic boundary disturbance. Hyperbolic tangent functions and saturation functions are adopted to tackle the input constraint. A restrained adaptive boundary iterative learning control (ABILC) law is proposed based on a time-weighted Lyapunov-Krasovskii-like composite energy function. In order to deal with the uncertainty of a system parameter and reject the external disturbances, three adaptive laws are designed and learned in the iteration domain. All the system states of the closed-loop system are proved to be bounded in each iteration. Along the iteration axis, the displacements asymptotically converge toward zero. Simulation results are provided to illustrate the effectiveness of the proposed ABILC scheme.

This paper presents a novel control scheme for trajectory tracking of valve-controlled electro-hydraulic actuators in lower limb load exoskeleton. First, the mathematical model of the electro-hydraulic system is developed in a strictly feedback form, where constant unknown mass and periodic unknown equivalent force acted on the electro-hydraulic actuator are involved. Then, under the framework of backstepping design, a controller consisting of an adaptive robust control and a repetitive learning control is proposed to learn the unknowns, respectively. The tracking convergence of the closed-loop system is proved rigorously in a Lyapunov way. Finally, the control performance of the proposed controller is verified via simuatlion.

Sensitivity loop shaping using add-on peak filters is a simple and effective method to reject narrow-band disturbances in hard disk drive (HDD) servo systems. The parallel peak filter is introduced to provide high gain magnitude in the concerned frequency range of open-loop transfer function. Different from almost all the known peak filters, which possess second-order linear system structures, in this paper we explore how high-order peak filters can be designed to improve the loop shaping performance. The main idea is to replace some of the constant coefficients of common second-order peak filter by frequency-related transfer functions, and then genetic algorithm (GA) is adopted to perform optimal pole and zero placement for those transfer functions. Owing to the remarkable searching ability of GA, the expected shape of sensitivity function can be achieved by incorporating the resultant high-order peak filter in parallel with baseline feedback controller. As an application, a well designed seventh-order peak filter is used to compensate contact-induced vibration in a high density HDD servo system, where the benefits of high-order filter are clearly demonstrated.