In Industry 5.0 vision, machines are empowered with the interaction capability to autonomously make local decisions and coordinate with each other as well as humans. However, how to form a group consensus on the rapid self-organizing of the manufacturing process is critical for achieving manufacturing resilience under disturbances and disruptions. Based on our formerly developed system ManuChain (Leng et al., 2020), this article proposes a blockchained smart contract system (BSCS), named ManuChain II, as the digital twin of a decentralized autonomous manufacturing system for achieving resilience in Industry 5.0. A blockchain-secured multiagent system architecture together with a product data model is established to form the BSCS. The BSCS could prevent tampering with data and enhance the transparency of the product manufacturing process. In BSCS, two types of blockchained smart contracts (SCs) are established with a bi-level interplay computing architecture. The lower-level contracts perform the predefined and learned patterns of task coordination for achieving resilience under internal disruptions. The upper-level contracts are incorporated with communication-efficient decentralized deep-learning algorithms for the learning, updating, transferring, and sharing of coordination patterns used in the autonomous decision in lower-level SCs, thereby achieving the continuous improvement of the system’s decentralized autonomous intelligence. Via incorporating the decentralized deep learning algorithms into blockchained SCs, this study reveals a new way to realize the self-organizing intelligence of the manufacturing system for enhancing resilience toward Industry 5.0.

This article aims to extend the theory of Lie subgroups and symmetric subspaces for studying an important class of submanifolds of the special Euclidean group SE(3) whose tangent space at each point on the submanifold relates to that at the identity by an adjoint map. These submanifolds, which we call adjoint-invariant submanifolds in this article, are known in the literature as persistent submanifolds, since they are strictly related to the concept of persistent screw systems. The difference is that in this article, just as Lie subgroups and symmetric subspaces, we put forward adjoint-invariant submanifolds as independent geometric objects from mechanisms and their associated local screw systems. Adjoint invariance relaxes the strict left and right invariance of Lie subgroups and the reflective invariance of symmetric subspaces by allowing generic moving reference frame in the aforementioned adjoint map. It turns out such adjoint invariance can be studied under the framework of distributions on manifolds, which allows us to explore global geometric properties of adjoint-invariant submanifolds. We classify adjoint-invariant submanifolds into reflective-type and product-type submanifolds and derive the conditions for their adjoint invariance. We then propose geometric methods and algorithms for synthesizing the kinematic generators for reflective-type submanifolds, as demonstrated with a number of examples.

A template matching (TM) algorithm has been widely employed in a visual inspection process of waferlevel flip-chip packaging, but the structures of traditional TM algorithms are always direct feedforward, which leads to the difficulty in achieving fast speed and high accuracy at the same time. The motivation of this article is to combine the ability to enable the chip visual measurement running in a fast-speed and high-accuracy manner. First, a novel selffeedback intelligent template matching (SFI-TM) structure is proposed, which can enable the intermediate information in the matching process to be fully utilized. The intelligent speed and resolution regulation rules are combined to construct the SFI-TM algorithm. Then, the reliability and robustness of the SFI-TM algorithm are theoretically analyzed to make sure it works in a stable manner. Finally, a series of practical chip alignment visual inspection experiments, including parameter testing, comparing experiments with the other five proposed visual detection algorithms, and robustness testing, are carried out in detail, respectively. The experimental results indicate that the SFI-TM algorithm can achieve the highest average measurement accuracy (1.08 μm) with almost the same measurement speed as fast as Tiny YOLOv2, and that it can resist the brightness variation from -20 to 30 gray value, the pepper-salt noise with a density of 0.5/pixel, and the Gaussian noise with a large variance of 2.5. In addition, it has good robustness against blurring and distortion of images under the dynamic speed motion processes.

The growth of individualized product demands drives high flexibility of manufacturing processes, which requires large-scale deployment of Industrial Internet of Things (IIoT). Since centralized control of IIoT suffers from poor flexibility in coping with disturbances and changes, a decentralized organization structure is a better choice, in which a permissioned blockchain-driven IIoT can enable partially decentralized self-organization and thus offload and accelerate the optimization of upper-level manufacturing planning. A novel iterative bi-level hybrid intelligence model named ManuChain is proposed to get rid of unbalance/inconsistency between holistic planning and local execution in individualized manufacturing systems. Lower-level blockchain-driven smart contracts proactively decentralize fine-grained and individualized task execution among machine tools via Raspberry Pi-based smart gateways and make the results available on an upper-level digital twin model for iterative coarse-grained holistic optimization. A prototype ManuChain based on a permissioned blockchain network is presented to realize both lower-level crowd self-organizing intelligence and upper-level holistic optimization intelligence.

Due to the excellent advantages of high speed and high precision, fast tool servo (FTS) system driven by piezoelectric actuators has great attraction for high-quality machining of microstructural array. However, its complex hysteresis nonlinearity at high speed will greatly affect the accuracy and stability of FTS system. Therefore, a stable autoregressive moving average (SARMA) model is proposed in this paper, which aims to describe the dynamic hysteresis nonlinearity accurately. First, a long autoregressive model residual calculation method is used to determine the order of the model and test the applicability of the model. Then, according to the Lyapunov stability theory, the strict stability analysis of the autoregressive moving average (ARMA) model is carried out in theory. By introducing the relaxation factor to transform the stability condition, the Lagrange multiplier and best square approximation method are applied to enhance the performance of the traditional ARMA model. Aiming at the difficulty of displacement sensor integration in FTS closed-loop controlling system, a hysteresis-compensated direct feedforward control strategy based on the proposed SARMA model is designed. Finally, a series of high-frequency trajectory tracking and comparing experiments has been carried out successfully with the traditional Prandtl-Ishlinskii (PI) and SARMA models to verify the effectiveness and superiority of the method. All results uniformly indicate that the SARMA model is nearly 20 times higher than the traditional PI model in terms of control accuracy and linearity, while the average linearity of FTS's dynamic tracking control is kept within 0.43% (265 nm), the stroke is 280 μm, and the positioning bandwidth is achieved up to 200 Hz.

Customer service is transforming from traditional manual service toward automated service, which utilizes different computational informatics to achieve a higher efficient and quality services. Automated customer service requires big data and expertise in data analysis as prerequisites. However, many companies, especially small and medium enterprises, do not have sufficient data and experience due to their limited scale and resources. They need to rely on third parties, and this reliance results in the lack of development of core customer service competency. In order to overcome these challenges, an open and automated customer service platform based on Internet of things (IoT), blockchain, and automated machine learning (AutoML) is proposed. The data are gathered with the use of IoT devices during the customer service. An open but secured environment to achieve data trading is ensured by using blockchain. AutoML is adopted to automate the data analysis processes for reducing the reliance of costly experts. The proposed platform is analyzed through use case evaluation. A prototype system has also been developed and evaluated. The simulation results show that our platform is scalable and efficient.

The problem of direct adaptive compensation for infinite number of time-varying actuator failures/faults is of both theoretical and practical importance in the fuzzy tracking control of uncertain nonlinear systems. However, due to the technical difficulties, so far, very limited result is available in addressing such an issue, which thus motivates us to propose a new fuzzy control methodology in this paper. The proposed scheme is established from the techniques of projection adaptation design, a new piecewise Lyapunov function analysis, and an optimized fuzzy adaptation. It is shown that all the closed-loop signals are bounded and the steady-state tracking error converges to a residual around zero, irrespective of a possibility that there are infinite number of time-varying actuator failures. Simulations are provided to illustrate the effectiveness and applicability of the proposed scheme.

Piezoelectric ceramics(PZT)actuator has been widely used in flexure-guided nanopositioning stage because of their high resolution. However, it is quite hard to achieve high-rate precision positioning control because of the complex hysteresis nonlinearity effect of PZT actuator. Thus, an online RELM algorithm with forgetting property(FReOS-ELM) is proposed to handle this issue. Firstly, we adopt regularized extreme learning machine(RELM)to build an intelligent hysteresis model. The training of the algorithm is completed only in one step, which avoids the shortcomings of the traditional hysteresis model based on artificial neural network(ANN) that slow training speed and easy to fall into the local minimum. Then, based on the regularized on-line sequential extreme learning machine(ReOS-ELM), an on-line RELM algorithm with forgetting property(FReOS-ELM) is designed, which can avoid the computational load of ReOS-ELM in the process of adding new data for learning on-line. In the experiment, a real-time voltage signal with varying frequencies and amplitudes is adopted, and the output displacement data of the nanopositioning stage is also acquired and analyzed. The results powerfully verify that the performance of the established hysteresis model based on the proposed FReOS-ELM is satisfactory, which can be used to improve the practical positioning performance for flexure nanopositioning stage.

This paper presents a deep learning-based model reduction method for distributed parameter systems (DPSs). The proposed method includes three phases. In phase I, numerical or experimental data of the spatiotemporal distribution is reduced into low-dimensional representations using the deep auto-encoder (DAE). In phase II, the low-dimensional representations are used to establish the reduced-order model. In phase III, the reduced model is then used to reconstruct the high-dimensional DPS. Experimental studies are conducted to validate the proposed method. The proposed method is compared with the classical proper orthogonal decomposition method and demonstrates better modeling accuracy and efficiency in the experiments.

This paper focuses on a problem of adaptive control for a class of nonlinear strict-feedback systems with a fuzzy dead zone and immeasurable states. By using the adaptive backstepping technique, an adaptive fuzzy output-feedback controller is constructed. The proposed control method requires only one adaptive law for an$n$th-order system. Compared with the conventional deterministic dead-zone models in previous articles, the main advantage of this paper is that the proposed dead-zone model is uncertain and fuzzy. By defuzzifying for fuzzy dead zone$\tilde{\Gamma }(u)$and employing an integrated design, an integrated fuzzy controller is constructed. It is proved that, even though the dead-zone input$\tilde{\Gamma }(u)$is fuzzy, the integrated fuzzy controller can make the closed-loop system semiglobally uniformly ultimately bounded and the tracking error converge to a small neighborhood of the origin. Finally, simulation results are provided to show the effectiveness of the proposed approach.

Optimal design is an inevitable step for parallel manipulators. The formulated optimal design problems are generally constrained, nonlinear, multimodal, and even without closed-form analytical expressions. Numerical optimization algorithms are thus applied to solve the problems. However, the optimization algorithms are usually chosen ad arbitrium. This paper aims to provide a guideline to choose algorithms for optimal design problems. Typical algorithms, the sequential quadratic programming (SQP) with multiple initial points, the controlled random search (CRS), the genetic algorithm (GA), the differential evolution (DE), and the particle swarm optimization (PSO), are investigated in detail for their convergence performances by using two canonical design examples, the Delta robot and the Gough-Stewart platform. It is shown that SQP with multiple initial points can be efficient for simple design problems, while DE and PSO perform effectively and steadily for all design problems. CRS can be used to generate good initial points since it exhibits excellent convergence evolution in the starting period.

This paper focuses on an input-to-state practical stability (ISpS) problem of nonlinear systems which possess unmodeled dynamics in the presence of unstructured uncertainties and dynamic disturbances. The dynamic disturbances depend on the states and the measured output of the system, and its assumption conditions are relaxed compared with the common restrictions. Based on an input-driven filter, fuzzy logic systems are directly used to approximate the unknown and desired control signals instead of the unknown nonlinear functions, and an integrated backstepping technique is used to design an adaptive output-feedback controller that ensures robustness with respect to unknown parameters and uncertain nonlinearities. This paper, by applying the ISpS theory and the generalized small-gain approach, shows that the proposed adaptive fuzzy controller guarantees the closed-loop system being semi-globally uniformly ultimately bounded. A main advantage of the proposed controller is that it contains only three adaptive parameters that need to be updated online, no matter how many states there are in the systems. Finally, the effectiveness of the proposed approach is illustrated by two simulation examples.

A novel three-domain fuzzy support vector regression (3DFSVR) is proposed, where the three-domain fuzzy kernel function (3DFKF) provides a solution to process uncertainties and input-output data information simultaneously. When compared with traditional two-domain SVR (2DSVR), the major advantage of 3DFSVR is able to use the prior knowledge via the novel fuzzy domain to analyze uncertain data and signals, which will enhance the potentials of 2DSVR. The 3DFKF is presented to integrate the kernel and fuzzy membership functions into a three-domain function. Definition and solution of the fuzzy convex optimization problem are presented to construct the whole theoretical framework. Experiments and simulation results show the effectiveness of 3DFSVR for the uncertain image denoising.

This paper investigates the fusion of unknown direction hysteresis model with adaptive neural control techniques in face of time-delayed continuous time nonlinear systems without strict-feedback form. Compared with previous works on the hysteresis phenomenon, the direction of the modified Bouc-Wen hysteresis model investigated in the literature is unknown. To reduce the computation burden in adaptation mechanism, an optimized adaptation method is successfully applied to the control design. Based on the Lyapunov-Krasovskii method, two neural-network-based adaptive control algorithms are constructed to guarantee that all the system states and adaptive parameters remain bounded, and the tracking error converges to an adjustable neighborhood of the origin. In final, some numerical examples are provided to validate the effectiveness of the proposed control methods.

An energy-efficient support vector machine (EE-SVM) learning control system considering the energy cost of each training sample of biped dynamic is proposed to realize energy-efficient biped walking. Energy costs of the biped walking samples are calculated. Then the samples are weighed with the inverses of the energy costs. An EE-SVM objective function with energy-related slack variables is proposed, which follows the principle that the sample with the lowest energy consumption is treated as the most important one in the training. That means the samples with lower energy consumption contribute more to the EE-SVM regression function learning, which highly increases the energy efficiency of the biped walking. Simulation results demonstrate the effectiveness of the proposed method.

An unscented Kalman filter (UKF)-based predictable support vector regression (SVR) learning controller is proposed to improve the flexibility of biped walking robots. After estimating the biped states of the next moment using a UKF, an SVR learning controller with the predicted biped states is implemented to ensure the zero moment point (ZMP) stability. Using the predicted biped states, the SVR learning controller can predictably adjust the posture of the trunk timely and properly to adapt to the dynamic posture of the whole body. The flexibility of biped robots is enhanced by the proposed method, which is promising for realizing the stable biped walking in unstructured environments. Simulation and experimental results demonstrate the superiority of the proposed methods.

This paper presents a novel approach aiming to dynamically maintain the collaboration ontology in the execution of an ontology-based federated collaborative product development system when a federate joins or has resigned from a given federation. The proposed approach includes two algorithms: ontology maintenance (+) and ontology maintenance (−), corresponding to joining and resigning situations. It adopts an axiom-based deduction ontology fusion strategy, and takes heavy-weighted ontologies into consideration. It can find all the explicit and derived inter-ontology relations, and furthermore it reaches the active upper bounds of implicit equivalent inter-ontology relations searching. This paper also discusses some implementation issues on the basis of TH_RTI, a RTI (Run Time Infrastructure) version developed by National CIMS ERC, Tsinghua University. The proposed approach has great potential to improve the efficiency of ontology-based federated collaboration executions, reduce the work load for adaptive adjustment of ever-existing platforms, and enhance the applicability and flexibility of collaborative product development systems.