Search

Due to the natural nonlinearity and unique memory characteristics, memristors are promising candidates for the construction of multi-scroll attractors having better application potential in the field of information encryption than the traditional double-scroll attractors. This paper proposes a novel memristive multi-double-scroll Chua's system (MMDSCS) via coupling a non-ideal flux-controlled memristor with multi-piecewise-linear memductance function in Chua's system directly. Specially, any number of multi-double-scroll chaotic attractors can be generated through adjusting the internal parameters of the memristor and without changing the original system's nonlinearity. Moreover, the amount of double scrolls is also closely related to the strength of the memristive coupling. Another highlight is that infinite initial offset-boosted coexisting Chua's double-scroll attractors with the same shape are produced with variation of the memristor initial conditions, indicating the emergence of an intriguing phenomenon of homogeneous extreme multistability. Furthermore, hardware experiments based on the field-programmable gate array (FPGA) are carried out to confirm the numerical simulations. Finally, an image encryption scheme is designed based on the memristor initial offset boosting dynamics. In comparison with the existing memristive Chua's systems, the proposed MMDSCS has many merits, such as memristor initial-controlled chaotic sequences with controllability and high security performance, which is more practical in applications.

The neutral grounding method is one of the crucial technologies used to ensure the safe and stable operation of distribution networks. With the development of power electronics-based devices, the application of highly controllable inverters to grounding systems has become a new research direction. In this review paper, based on the summary and analysis for the research status, a flexible grounding system is systematically classified according to its control strategy and structure. And then, the following core technologies are summarized: faulted line selection, current component detection, high-resistance ground identification, ground parameter measurement, neutral point voltage control, and fault location. Subsequently, deficiencies of flexible grounding systems are summarized from the following four perspectives: reliability, accuracy, speed, and stability. Finally, some discussions and recommendations for future development and research direction are presented. Especially, the reliability-enhanced hybrid grounding system that combines active inverters and low resistance for high-resistance ground faults is recommended. This paper provides a systematic literature review of the crucial technologies for flexible grounding systems and can be used as a technical reference for future research.

Memristors are widely used to construct multi-scroll/wing chaotic systems with complex dynamics. However, the generation of a multi-scroll/wing attractor is typically not induced by the memristor but depends on other nonlinear functions in the system, which does not take advantage of the unique features of the memristor for chaos-based applications. To address this issue, the present paper introduces a memristor coupling (MC) method to construct a novel memristive Sprott A system (MSAS) through coupling a flux-controlled memristor with multi-piecewise linear memductance into the chaotic Sprott A system. From theoretical analysis and numerical simulations, the MSAS is shown to be able to generate any number of multi-type hidden attractors, including multi-one-scroll, multi-double-scroll and multi-double-wing hidden attractors. In addition, it has two kinds of multistabilities, that is, heterogeneous multistability and homogeneous multistability. Based on these unique properties, different numbers of coexisting heterogeneous hidden attractors and coexisting homogeneous hidden attractors are derived respectively by switching the memristor initial states. These interesting dynamical properties are comprehensively investigated using nonlinear analysis tools. Furthermore, hardware experiments are implemented to demonstrate the feasibility of the MSAS and the effectiveness of the MC method. Finally, a new pseudo-random number generator (PRNG) is proposed to explore the practical applications of the MSAS. Performance evaluation results verify the high-quality randomness of the designed PRNG.

Robot navigation in a dynamic environment is a challenging task because not only the safety but also the comfort of surrounding pedestrians shall be necessarily considered. This paper proposes the concept of social stress based on tension space of robot and human, which is an important part of Human-Robot interaction. Especially, the proposed approach develops crowd-comfort navigation by combining social stress indexes with a deep reinforcement learning framework and the value network. A set of typical simulation experiments show that our method improves the comfort of surrounding pedestrians effectively during the process of robot navigation. In addition, the fine-tuned technology proposed in this paper has also been proven to be suitable for different scenarios.

In urban distribution networks, due to its strong reliability and simple operation, the low-resistance grounding system has gradually replaced the resonance grounding system represented by Petersen coil. However, when a high-resistance ground fault occurs, it is difficult for the low-resistance grounding system to identify the smaller fault characteristics, and the zero-sequence protection device cannot ensure the system reliability. In this letter, a hybrid grounding system (HGS) combining the active neutral-point voltage regulator (NVR) and low-resistance is proposed. By injecting compensation voltage into the neutral point, the fault phase voltage can be reduced below the threshold that can generate a fault arc. Additionally, the proposed coordinated control strategy can effectively switch between the two operation modes (active NVR and low-resistance) according to the actual fault types. Simulation and experimental results verify the rationality and effectiveness of the proposed concept and analysis.

This paper is concerned with the intermittent fault (IF) detection problem for a class of linear discrete-time stochastic systems over sensor networks with constant time delay. By utilizing the lifting method, the distributed decoupled observers are proposed based on the output information of neighbor nodes and the node itself. In order to detect the appearing time and disappearing time of the IF, the truncated residuals are designed by introducing a sliding-time window. Furthermore, the IF detection and location thresholds are determined based on the hypothesis testing technique and the detectability of the IF is analyzed in the framework of stochastic analysis. Finally, a simulation example is presented to illustrate the effectiveness of the derived results.

Non-parallel text style transfer has attracted increasing research interests in recent years. Despite successes in transferring the style based on the encoder-decoder framework, current approaches still lack the ability to preserve the content and even logic of original sentences, mainly due to the large unconstrained model space or too simplified assumptions on latent embedding space. Since language itself is an intelligent product of humans with certain grammars and has a limited rule-based model space by its nature, relieving this problem requires reconciling the model capacity of deep neural networks with the intrinsic model constraints from human linguistic rules. To this end, we propose a method called Graph Transformer–based Auto-Encoder, which models a sentence as a linguistic graph and performs feature extraction and style transfer at the graph level, to maximally retain the content and the linguistic structure of original sentences. Quantitative experiment results on three non-parallel text style transfer tasks show that our model outperforms state-of-the-art methods in content preservation, while achieving comparable performance on transfer accuracy and sentence naturalness.

Metro tunnels play a crucial role in urban transportation. However, with growing tunnel operation periods, defects, and large deformations appearing, these are influencing tunnel structural performance and threatening public safety. Three-dimensional (3D) tunnel reconstruction is an effective way to highlight tunnel conditions and provide a basis for engineering management and maintenance. However, the current methods of tunnel 3D reconstruction do not sufficiently combine the qualitative and quantitative characteristics of tunnel states. In this study, a novel method for metro tunnel 3D reconstruction based on structure from motion (SfM) and direct linear transformation (DLT) is proposed. The dimensionless 3D reconstruction point cloud acquired through the SfM method showcases the qualitative characteristics (such as leakage and pipelines) of the tunnel state. The close-range photogrammetry DLT method provides scale information missing from the SfM method and quantitative characteristics (such as profile deformation) of the tunnel state. The SfM-DLT method was tested in a Shanghai metro tunnel, and proved to be feasible and promising for future tunnel inspections.

Acoustic-based diagnosis (ABD) is a promising method for machinery fault detection due to its ability to overcome the limitation of vibration measurement through non-contact measurement by air couple. However, most of the ABD approaches are not widely used in real industrial scenario due to the limitation of strong and highly non-stationary background noise interference. To address the shortcoming, a novel ABD method based on recursive denoising learning (RDL) is proposed in this article. In the proposed method, a new multistage attention mechanism is designed as the fundament of RDL for adaptive tracking and estimating non-stationary industrial background noise and automatic suppressing noise. Based on the multistage attention mechanism, a novel recursive learning strategy is introduced to further improve the performance of noise suppression by recursive tracking noise component and gradual denoising in coarse-to-fine manner. Then, an information fusion method, which is based on an improved tiny-shuffle network (TSN), is adopt to increase the discriminative representation of fault feature through fusion of multi-channel denoising information for improving diagnosis accuracy. Afterward, an RDL-based fault diagnosis method is finally obtained by combining with a standard fault diagnosis model, and it eventually achieves good performance for detection gear fault pattern in noise interference environment. The experimental results in both real industrial background noise condition and additive white Gaussian noise (AWGN) condition with different signal-to-noise ratios (SNRs) indicate that the proposed method performs better than all other popular methods in noise suppression and gear fault pattern detection, which verify the effectiveness of the proposed ABD method in dealing with gear fault diagnosis task under noise condition.

The burden charging operation in blast furnace is one of the most important operations during iron-making process. In this paper, we focus on the study of precise burden charging operation, which involves two aspects: How to obtain and form the optimal burden surface shape. For the first problem, we construct a mapping model between the burden surface characteristic parameters and the comprehensive operational performance indicators of the blast furnace, and transform the search of optimal burden surface shape into the target optimization problem. The second problem refers to establishing a suitable burden charging strategy based on the basic burden surface and the optimal burden surface. In our work, by adaptively adjusting the opening degree of the throttle valve, it is possible to control accurate burden volume during the rotation of the charging chute, which can make sure to spill the appropriate burden volume on the suitable charging units. In the simulation of experiments, we collected the real industrial data during iron-making process and demonstrated the efficiency of the proposed model.

Memristors are widely considered to be promising candidates to mimic biological synapses. In this paper, by introducing a non-ideal flux-controlled memristor model into a Hopfield neural network (HNN), a novel memristive HNN model with multi-double-scroll attractors is constructed. The parity of the number of double scrolls can be flexibly controlled by the internal parameters of the memristor. Through theoretical analysis and numerical simulation, various coexisting attractors and amplitude control are observed. Particularly, the interesting and rare phenomenon of the memristor initial offset boosting coexisting dynamics is discovered, in which the initial offset boosting coexisting double-scroll attractors with banded attraction basins are distributed in a line along the boosting route with the variation of the memristor initial condition. In addition, it is also found that the number of the initial offset boosting coexisting double-scroll attractors is closely related to the total number of scrolls and ultimately tends to infinity with increasing the total number of scrolls, meaning the emergence of extreme multistability. Then, the random performance of the initial offset boosting coexisting double-scroll attractors is tested by the NIST test suite. Moreover, an encryption scheme based on them is also proposed. The obtained results show that they have excellent randomness and are suitable for image encryption application. Finally, numerical simulation results are well demonstrated by circuit experiments, showing the feasibility of the designed memristive multi-double-scroll HNN model.

Hot metal silicon content is an important indicator for measuring the smooth operation of the blast furnace. However, the hot metal silicon content cannot be directly detected online. Hence, this paper proposes a prediction model of the hot metal silicon content based on the improved multi-layer online extreme learning machine (ML-OSELM). The improved ML-OSLEM algorithm is based on ML-OSELM, the variable forgetting factor (VFF) and the ensemble model. VFF is introduced to make the new coming data get more emphasis. The ensemble model can overcome the overfitting problem of ML-OSELM. This improved algorithm is named as EVFF-ML-OSELM. The real blast furnace production data are used to testify the established prediction model based on EVFF-ML-OSELM. Compared with the prediction models of the hot metal silicon content based on other algorithms, the simulation results demonstrate that the prediction model based on EVFF-ML-OSELM has better prediction accuracy and generalization performance.

In this article, we study solder paste inspection (SPI), an important stage that is used in the semiconductor manufacturing industry, where abnormal boards should be detected. A highly accurate SPI can substantially reduce human expert involvement, as well as reduce the waste in disposing of the boards in good condition. A key difference today is that because of increasing demand in board customization, the number of board types increases substantially and quantity of the boards produced in each type decreases. Thus, the previous approaches where a fine-tuned model is developed for each board type are no longer viable. Intrinsically, our problem is an anomaly detection problem. A major specialty in today’s SPI is that the target tasks for prediction cannot be fully pre-determined due to context changes during the solder paste printing stage. Our experiences show that a conventional approach to first define a set of tasks and train these tasks offline will lead to low accuracy. Here, we propose a novel multi-task approach, where the performance of all target tasks is ensured simultaneously. We note that the SPI process is streamlined and automatic, allowing the SPI time for only a few seconds. We propose a fast clustering algorithm that reuses existing models to avoid retraining and fine tune in the inference phase. We evaluate our approach using 3-month data collected from production lines. We show that we can reduce 81.28% of false alarms. This can translate to annual savings of $11.3 million.

Power electronicconverters have attracted significant attention in renewable energy generation and distribution systems. However, some crucial techniques, such as power quality and stability enhancement of converters, still need to be further improved. In this study, an improved reduced-order generalised integrator (ROGI), which can achieve decoupling, is proposed. It can reduce the α -axis and β -axis current coupling and improve the dynamic response performance, maintaining the advantage of the conventional ROGI (e.g. less computational burden). Besides, delay compensation is added to the proposed decoupled ROGI, which improves the stability of the current loop and can be effectively applied for the current/voltage harmonic suppression in the distributed system. Also, the procedures of parameter tuning and optimal delay compensation angle computation are given. Finally, the harmonic current compensation of the three-phase grid-connected converter is taken as an example for simulation analysis, and the experimental results verify the reasonability and effectiveness of the proposed method.

In this paper, an intelligent data-driven optimization scheme is proposed for finding the proper burden surface distribution, which exerts large influences on keeping blast furnace running smoothly in an energy-efficient state. In the proposed scheme, production indicators prediction models are first developed using a kernel extreme learning machine algorithm. To heel, burden surface decision is presented as a multiobjective optimization problem for the first time and solved by a modified two-stage intelligent optimization strategy to generate the initial setting values of burden surface. Furthermore, considering the existence of the approximation error of the created prediction models, feedback compensation is implemented to enhance the reliability of the results, in which an improved association rule mining method is developed to find the corrected values to compensate the initial setting values. Finally, we apply the proposed optimization scheme to determine the setting values of burden surface using actual data, and experimental results illustrate its effectiveness and feasibility.

This study investigates the problem of intermittent fault (IF) detection for a class of discrete-time linear stochastic systems (LSSs) with time delay. The IF has the characteristics of intermittency, randomness and uncertainty, and the time delay is constant. By using the lifting method and a reduced-order observer, the truncated residual over a sliding-time window is presented for the IF detection of discrete-time LSSs with time delay. Two hypothesis tests are proposed to set the thresholds for detecting the appearing (disappearing) time of IF. Moreover, the magnitude of IF is estimated and the detectability of IF is analysed based on the analysis of statistical characteristics of the truncated residual. The efficacy and practicality of the derived detection scheme are verified via a numerical simulation of the Williams–Otto process.

In this paper, we develop a data-driven algorithm to learn the Nash equilibrium solution for a two-player non-zero-sum (NZS) game with completely unknown linear discrete-time dynamics based on off-policy reinforcement learning (RL). This algorithm solves the coupled algebraic Riccati equations (CARE) forward in time in a model-free manner by using the online measured data. We first derive the CARE for solving the two-player NZS game. Then, model-free off-policy RL is developed to obviate the requirement of complete knowledge of system dynamics. Besides, on- and off-policy RL algorithms are compared in terms of the robustness against the probing noise. Finally, a simulation example is presented to show the efficacy of the presented approach.

In this paper, the cost allocation problem of minimum spanning tree without a supplier has been discussed. By assigning nodes to play the role of supplier in turn, we can get n classic m.c.s.t.s. A cooperative cost game model is established whose cost function is defined on cost functions of the n classic m.c.s.t.s. We show that the cooperative game is totally balanced and it has a large core that includes each irreducible core of the classic m.c.s.t. mentioned above. As for a specific core allocation, the arithmetic mean of all Bird imputations is recommended.

Automated tire visual inspection plays an extraordinary important role in ensuring tire quality and driving safety. Due to the anisotropic complex multi texture and defect diversity characteristic of tire radiographic image, tire intelligent visual inspection has become one of the technical bottlenecks of intelligent manufacturing. In this work, a novel tire defect detection model using Concise Semantic Segmentation Network (Concise-SSN) is investigated for automated tire visual inspection. We perform an end-to-end pixel-wise tire defect detection by combining the power of an optimized semantic segmentation network and a compact convolutional neural network for classification. It can achieve the end-to-end pixel-wise full class defect detection and classification. The experimental results show superior performance on defect segmentation and classification tasks compared to state-of-the-art models with smaller model size and faster computation. Comparative experiments indicated that our Concise-SSN achieves the mPA score of 85.13%, the mIoU score of 77.34% on our test set. The accuracy of defect classification is 96.5% on average. Finally, we show faster computation (0.132 seconds per image) with competitive results on our dataset, which can meet the needs of online tire detection.

Collaborative filtering (CF) is the most classical method for recommender system, but it is usually suffered from limited performance by the sparseness of user-to-item rating data. Recently, due to the powerful learning feature representation ability, deep learning components are used to leverage auxiliary information to assist recommendation. However, most existing models based on deep learning are incomplete so that merely extracting the item latent representation and ignoring the user parts. Besides, different data are not chosen from current models. This paper proposes a novel probability framework, named as joint matrix factorization (JMF). There are three components in JMF. Firstly, the modified multilayer crossing version of the factorization machine (MFM) is designed to extract the user latent factors based on user behavior information. Moreover, MFM is a general method which can be used to accomplish many tasks in terms of machine learning. Secondly, a modification of Long Short-Term Memory (LSTM), named as bidirectional LSTM (BLSTM), is used to extract the item latent factors of a document sequence from both front and back directions. Finally, we tightly integrate BLSTM and MFM into probabilistic matrix factorization (PMF) to form JMF. Compared with the classical matrix factorization and other integration models, JMF extracts document data as well as user behavioral data as item vectors and user vectors. Extensive experiments on five real-world datasets show the proposed model has better performance compared with the state-of-the-art recommendation methods.

Composite adaptive control schemes, which use both the system tracking error and the prediction error to drive the updating law, have become widespread in achieving an improvement of system performance. However, a strong persistent-excitation (PE) condition is required to guarantee the convergence of the parameter estimation errors. This paper proposes a novel composite adaptive control for nonlinear teleoperation systems with dynamic uncertainties and time-varying communication delays, by which the parameter convergence is achieved without the PE condition. The novelty lies in the construction of the prediction errors by designing lower-bounded gain matrices of the prediction errors. The stability criteria of the closed-loop teleoperation system are given in terms of linear matrix inequalities. Simulation studies are given to show the effectiveness of the proposed method.

Augmented reality is a research hotspot developed on the basis of virtual reality. Friendly human-computer interaction interface makes the application prospect of augmented reality technology very broad. Convolutional neural networks in deep learning have been widely used in the field of computer vision and become an important weapon in dynamic image recognition tasks. Combining deep learning and traditional machine learning techniques, this article uses convolutional neural networks to extract features from image data. The convolutional neural network uses the last layer of features and uses the softmax recognizer for recognition. This article combines a convolutional neural network that can learn good feature information with integrated learning that has good recognition effects. In the recognition tasks of the MNIST database and the CIFAR-10 database, comparison experiments were performed by adjusting the hierarchical structure, activation function, descent algorithm, data enhancement, pooling selection, and number of feature maps of the improved convolutional neural network. The convolutional neural network uses a pooling size of 3*3, and uses more cores (above 64), small receptive fields (2*2), and more hierarchical structures. In addition, the Relu activation function, gradient descent algorithm with momentum, and enhanced data set are also used. The research results show that under certain experimental conditions, the dynamic image recognition results have dropped to a very low error rate in the MNIST database, and the error rate in the CIFAR-10 database is also ideal.

Burden surface distribution plays a key role in achieving an energy-efficient status of blast furnace (BF). However, actual adjustment of burden surface usually depends on the operator's experience when the production status changes. Meanwhile, due to the characteristics of high dimension, strong coupling, and distributed parameters, it is difficult to establish the accurate mechanism model for BF ironmaking process. Considering the aforementioned issues, this paper proposes an integrated multi-objective optimization framework for optimizing burden surface distribution based on the analysis of BF operation characteristics. Firstly, data-driven models are constructed for two objectives, i.e., gas utilization ratio (GUR) and coke ratio (CR), and two constraints using adaptive particle swarm optimization (APSO) based extreme learning machine (ELM), named APSO-ELM. Multi-objective optimization is subsequently carried out between GUR and CR using the multi-objective differential evolution algorithm (MODE) to generate the Pareto optimal solutions. Finally, TOPSIS is applied to select a best compromise solution among the Pareto optimal solutions for this optimization problem. Comprehensive experiments are presented to illustrate the performance of the proposed integrated multi-objective optimization framework. The experimental results demonstrate that the proposed framework can give a reasonable burden surface profile according to the production status changes to guarantee the BF operation more efficient and stable.

The self-encoder is a typical unsupervised deep learning algorithm. In the field of unsupervised learning, it is very popular with researchers. Therefore, in view of the shortage of labeled training samples, the convolution kernel of a typical convolutional neural network is set by experience, and the network structure is fixed and it is difficult to re-learn later. This paper combines the convolutional neural network and the automatic encoder, and proposes a multi-based the method of integrated network structure to extract the features of the image for recognition. First, the SAE pre-trained CNN model convolution kernel is used to pre-train based on the classic CNN structure. Secondly, input and process image data of different scales to extract image space and spectral features respectively. Then, construct multiple channels, and use different scale filters and sampling intervals for different channels. Finally, after one layer of down sampling, the feature maps obtained from multiple channels are input into the fully connected layer, and after a hidden layer, the features finally used for classification are obtained. Experimental results show that the proposed method uses sparse automatic coding for pre-training time efficiency increased by 50%, and can further improve the recognition accuracy, the highest recognition rate reached 0.985.

Testing the health of tunnels, as a branch of highway operation, has an extremely important application in public property and even life safety. Among them, there are many factors that cause the tunnel to deform or collapse. The conventional methods use the finite element method (FEM) which are to simulate the bearing capacity loss rate of the lining by using the mechanical method. However, it takes a long time to calculate the stress-strain-situation of the lining model under each condition. This paper explores the machine learning to calculate the loss rate of the lining bearing capacity under more conditions based on FEM simulation data. Here, we establish a machine learning toolbox for modeling the loss rate of the lining bearing capacity named “MLLBC”, which contains three main components: 1) data loading; 2) machine learning model deployment; 3) performance evaluation. To ensure the fairness of model evaluation, ten machine learning models use a unified code library. We also conduct experiments on our new dataset which is the loss rate of the lining bearing capacity with different data amounts, as well as experiments on the goodness of model fitting under different ranges of various variables.

In industrial production, there are strict requirements for the braking effect of heavy transport equipment such as elevator and belt conveyor. The working capacity and reliability of the brake are the basis for ensuring efficient production. Based on the friction and wear test, taking the average friction coefficient and stable wear rate as the key parameters to measure the reliability and stability of the brake, the friction and wear characteristics of the hydraulic disc brake of the hoist under different working conditions are analyzed and studied. The results shows that the average friction coefficient and stable wear rate of the brake fluctuate less with the change of brake pressure in the middle speed range. At this time, the adhesive and matrix fiber in the friction pad have not been decomposed and modified, and the strength and shape of the surface micro convex structure are relatively moderate, so the braking reliability is in good condition.

Theoretical or numerical progressive collapse analysis is necessary for important civil structures in case of unforeseen accidents. However, currently, most analytical research is carried out under the assumption of material elasticity for problem simplification, leading to the deviation of analysis results from actual situations. On this account, a progressive collapse analysis procedure for truss structures is proposed, based on the assumption of elastoplastic materials. A plastic importance coefficient was defined to express the importance of truss members in the entire system. The plastic deformations of members were involved in the construction of local and global stiffness matrices. The conceptual removal of a member was adopted, and the impact of the member loss on the truss system was quantified by bearing capacity coefficients, which were subsequently used to calculate the plastic importance coefficients. The member failure occurred when its bearing capacity arrived at the ultimate value, instead of the elastic limit. The extra bearing capacity was embodied by additional virtual loads. The progressive collapse analysis was performed by iterations until the truss became a geometrically unstable system. After that, the critical progressive collapse path inside the truss system was found according to the failure sequence of the members. Lastly, the proposed method was verified against both analytical and experimental truss structures. The critical progressive collapse path of the experimental truss was found by the failure sequence of damaged members. The experimental observation agreed well with the corresponding analytical scenario, proving the method feasibility.

Vital signs such as heartbeat and respiration signals are significant indicators for health care and clinical applications. Non-contact vital signs detection via mm-wave radar has attracted more attention due to more comfortable experience and lower burden. However, the non-contact heartbeat and respiration signals detection with random body movements is more challenging. In this paper, we propose a general framework to address this problem. It is termed DRSEPK and consists of signal decomposition and reconstruction, spectrum estimation and spectral peak tracking. Signal decomposition and reconstruction is applied for denoising and reconstructing cleaned signal. Spectrum estimation aims to get high-resolution frequency spectrum. The spectral peak tracking can select correct spectral peaks corresponding to breath rate (BR) and heartbeat rate (HR). Experiments are conducted using frequency modulated continuous wave (FMCW) radar on ten subjects who are typing on a laptop. The results show that the DRSEPK framework has high estimation accuracy and is reliable for non-contact vital signs detection during random body movements.

To realize real-time weapon trajectory in VC, the paper compares various methods and selects NI Measurement Studio with Visual C++ tool kit. The using ActiveX technology not only including the combine of NI graph control with VC, the development of high-efficiency and practical trajectory graph realization method were also included. Applying the method into practical project it gains operation of VI graph control, it changesextreme values of graph control to realize trajectory’s zooming and moving.Practical application verifies validity and advantage of the method.

In the soft switch inverter system, the core part is the lower computer of the main chip with the TMS320F28335 DSP. In order for the operator to issue the command control system operation and intuitively reflect the operating performance of the system, this paper applies virtual instrument technology to soft switch inverter system and designs the software of the upper computer of soft switch inverter system with the help of the powerful graphics control of virtual instrument. The upper computer and the lower computer realize information interaction through CAN communication. On the upper computer, the motor operation status is displayed using control software written by Lah/Windows CVI. The upper computer sends instructions such as rotation speed setting according to the system’s needs. Through experiments, the correctness and reliability of the upper computer software are verified.

Photovoltaic power (PV) generation systems connected to distribution network are able to effectively absorb local solar energy and improve the reliability of power supply. The virtual synchronous generation (VSG) technology used in inverter of the PV can help it improve the ability of connecting to power system by increasing system inertia and damping. This paper proposes an optimized VSG control strategy which is based on spatial phase analysis to solve the fault problem of PV system facing unbalanced voltage fault in grid so that the reliability of PV system can be improved. In details, the proposed strategy is able to control the fault current and reduce second harmonic component of power of PV system connected to grid by analyzing different vectors affecting different electrical parameters. The simulation carried on PSCAD/EMTDC proves the effectiveness and superiority of proposed improved VSG strategy compared with P/Q and normal VSG strategy.

Burden distribution is an important method to regulate the operation state of blast furnace. Reasonable burden distribution matrix of blast furnace is the prerequisite for improving resource utilization and ensuring stable blast furnace condition. In order to achieve the above target, an ensemble prediction model based on weighted voting and a method of calculating weights are proposed in this paper. In this model, the convolution neural network (CNN) - bidirectional gated recurrent unit (BiGRU) based on attention mechanism, logistic regression, k-nearest neighbor (KNN) and support vector machines (SVM) are integrated to predict whether the burden distribution matrix of blast furnace needs to be adjusted. The weight of each individual model is determined by its prediction accuracy and F1-score. CNN converts the extracted feature vectors into time series and inputs them into BiGRU. The attention mechanism is introduced to assign different weights to the hidden state of BiGRU, so as to enhance the long-term influence of important information. Finally, the production data of blast furnace are used to testify the performance of prediction models. In this paper, Multilayer Perceptron (MLP) model, RNN model, BiGRU model, BiGRU model based on attention mechanism, logistic regression model, KNN model, SVM model and the proposed ensemble model are used for comparison experiments, compared with other prediction models, the experimental results illustrated that the weighted voting ensemble prediction model can accurately determine whether the burden distribution matrix of blast furnace needs to be adjusted and have better prediction accuracy and generalization performance.

For the self-supervised image depth estimation algorithm based on deep learning, the characteristics of self-supervised methods cause some problems such as visual shadow and infinity estimation. This paper tackles these problems by adopting the spatial consistency loss and multiple loss constraints. In this paper, the depth estimated network and pose estimated network are trained by binocular image sequence. And the depth estimated problem is transformed into image reconstruction and scene reconstruction to realize self-supervised training. Based on the Deep Convolutional Neural Networks(DCNN), the depth estimated network introduces the Deep Atrous Convolution (DAC) and the Atrous Spatial Pyramid Pooling (ASPP) modules to extract the multi-scale feature and increase the receptive field of the network. The spatial consistency of scene reconstruction strategy greatly reduces the estimated error of pose network. The quantitative and qualitative evaluation on the KITTI dataset shows that the proposed algorithm outperforms the existing self-supervised depth estimation algorithms in accuracy and error, even exceeds most of the supervised algorithms.

As the prodromal stage of Alzheimer's disease, effective recognition of mild cognitive impairment can reduce the prevalence of Alzheimer's disease. At present, most of the research on the recognition of mild cognitive impairment is carried out through biomarkers and neuroimaging, which is not conducive to large-scale analysis and research. Based on neuropsychological evaluation and life habits questionnaires, this article applies machine learning methods to the recognition of mild cognitive impairment and conducts experimental research. A questionnaire survey of the elderly was conducted to obtain raw data, including demographic variables, daily habits and neuropsychological data. Feature selection is carried out through filter screening method and the influence of factors such as lifestyle, physical health and learning ability on the morbidity of mild cognitive impairment is analyzed. The classifier mainly uses three methods: artificial neural network, support vector machine and random forest. The experimental results show that the random forest classification effect is the best and the accuracy rate is as high as 92%. Artificial neural network has strong generalization ability with 91% accuracy rate. Support vector machine has inferior effect.

With the thriving of network embedding, link prediction based on network embedding has received increasing attention in recent years. Network embedding aims to learn the low dimensional vertex representations in a network while preserving the structures and inherent properties of the network. While the latent benefits of learning low dimensional representations can be tremendous for link prediction, improper releasing vertex representations may pose privacy of network individuals. Presently, protecting individual's privacy in network embedding has been largely unexplored. Addressing this goal, we propose a spectral clustering (SC) based differentially private network embedding for link prediction, namely DPHWSC. In this approach, we first present a SC based solution to reap the vertex representations. Meanwhile, the proximities of arbitrary orders can be captured and different orders of proximities can be arbitrarily weighted. Then, we leverage a sampler to approximate global sensitivity of vertex representations with high probability, achieving random differential privacy. Extensive experiments demonstrate that DPHWSC can not only yield high prediction precision, but also ensure a reliable level of privacy protection.

We propose a cost-effective digital coherent scheme with low-complexity digital signal processing (DSP) for short-reach optical interconnection. Differential 8-ary quadrature amplitude modulation (D8QAM) with 1-decision-aided adaptive differential decoding bypasses carrier recovery and enables cycle-slip-free operation. We experimentally demonstrate that the receiver sensitivity of 400-Gb/s D8QAM is insensitive to the laser type, and is the same as 400-Gb/s 16QAM in the case of 2-km transmission with a distributed feedback (DFB) laser. The proposed adaptive equalizer (AEQ) using real-valued finite impulse response (FIR) filters and shorter tap lengths for the real-imaginary filters allows hardware-efficient implementation with high robustness to the receiver-side timing skew. In the case of 400-Gb/s D8QAM 10-km transmission, our AEQ achieves comparable performance as conventional 4×4 real-valued multi-input multi-output (MIMO) and the existing simplified AEQs with complexity reduction of 50% and 14% respectively.

This paper investigates fixed-time attitude tracking maneuver of rigid spacecraft in the presence of actuator faults, external disturbances, and inertia uncertainties. First, a fast finite-time stable system is investigated in the sense of fixed-time concept. Then, a nonlinear observer is designed to estimate the information of the lumped uncertainties, and this observer, integral sliding mode and geometric homogeneity are used to formulate one attitude controller, which can guarantee attitude tracking errors can be stabilized to the origin. Second, another adaptive controller is presented to steer attitude tracking errors to the equilibrium point. Lyapunov techniques are implemented to ensure the fixed-time stability of the closed-loop system. Finally, numerical simulations are carried out to demonstrate the performance of the proposed controllers.

Traditional nonlinear process monitoring approaches deal with all process variables directly, without carefully investigating their complex relationships. In this Article, key performance indicator...

Aiming at the problem of heat dissipation performance of disc brake, a computer simulation method is used to analyze the braking process. Taking ventilated brake disc as the research object, four geometric models of ventilated brake disc with different arrays and shapes were established. Considering typical braking conditions, the heat dissipation characteristics of ventilated brake discs were simulated by computational fluid dynamics (CFD). The influence of array mode and shape of rib heat dissipation structure on heat dissipation characteristics of ventilated brake disc is analyzed. The results show that the array mode of the rib plate heat dissipation structure in the radial ventilation duct has a great influence on the heat dissipation characteristics of the brake disc. In the ventilation duct of the triangular array ribbed heat dissipation structure, there is less air resistance, stronger turbulence, less flow separation, higher convective heat transfer coefficient and heat flux.

In the past century, low Reynolds number airfoil design for both military and civil applications has continued to capture the interest of practitioners of applied aerodynamics. A new design methodology for airfoils has been developed, which controls the airfoil profile through 8 parameters. The airfoil aerodynamic characteristics were predicted through the XFOIL code, to optimize airfoil under mode-FRONTIER environment. The reliability verification result predicted that the XFOIL code can be used to determine the airfoil performance in the linear segment of the lift coefficient curve. Application of this methodology was demonstrated through two cases. For Case-I, airfoils design were based on E387 airfoil profile and synthetic aerodynamic performance at different angles of attack for Re = 2.0 × 10 5 were considered. While for Case-II, designed airfoils were based on PSU 94-097 airfoil with synthetic aerodynamic performance at different angles of attack for Re = 4.0 × 10 5 . Results of both cases showed enhanced aerodynamic properties for the designed airfoils.

The topic associated with hidden attractor and multistability has been received considerable attention recently. In this paper, a novel no-equilibrium Jerk-like chaotic system is constructed and explored. Particularly, owing to the absence of the equilibria, such a new system can be categorized as a system with hidden attractors. More interestingly, this system holds three conspicuous characteristics. The first one is that various asymmetric coexisting hidden attractors and complicated transient chaos behaviors are obtained. The second one is the new finding of the periodic bursting oscillation and unusual phenomenon of transient periodic bursting oscillation in the system. The third one is the observation of the amazing and rare phenomenon of one to two full Feigenbaum remerging trees, namely, antimonotonicity. To the best knowledge of us, the last two special features are first discovered and have never been reported, especially in such no-equilibrium chaotic system that exhibits hidden attractors. With the help of phase portraits, time series, bifurcation diagram, Lyapunov exponents, chaotic dynamical diagram, basin of attraction and so forth, the rich hidden dynamical properties of this system are systematically analyzed and investigated. Additionally, a hardware electronic circuit on a breadboard is carried out. A very good similarity between the hardware experimental results and the theoretical analysis testifies the feasibility and practicality of this original system.

The whale optimization algorithm(WOA) is a novel meta-heuristic evolutionary algorithm inspired by the behavior of whales predation. An important factor to the success of WOA is the balancing between exploration and exploitation. In the WOA, the distance control parameter $a$ is the main factor to find an appropriate balance between exploration and exploitation. In the standard WOA, the distance control parameter $a$ is optimized by linear control strategy (LCS), but the process of whales predation is not simply linear process. To address the issue, this paper proposed a nonlinear control strategy based on arcsine function (NCS-Arcsin) to optimize WOA. The NCS-Arcsin is applied to adjust distance control parameter $a$ . The NCS-Arcsin is considered to accurately describe the process of whales predation. Experiments on twelve well-known benchmark functions show the NCS-Arcsin can significantly improve the exploration and exploitation capabilities of WOA. In addition, the performance of proposed NCS-Arcsin is compared with LCS and other have been proposed NCS. The experimental results show that the optimization effect of NCS-Arcsin is stronger than that of LCS and other NCS. The NCSs based on the arcsine function is the best NCS, which can significantly improve the optimize performance of WOA.

This research work reports a double-wing chaotic system with a line of equilibrium points and constructs an electronic circuit via MultiSIM for practical implementation. Explicitly, the new chaotic system has a total of six terms with two quadratic nonlinearities and absolute function nonlinearity. Using the phase plots in MATLAB, we demonstrate that the new chaotic system has double-wing chaotic attractor. We describe the Lyapunov exponents and the Kaplan-Yorke fractal dimension of the new chaotic system. A novel feature of the new chaotic system is that the system has rest points located on the z-axis as well as two rest points not on the z-axis. Thus, the new system has infinite number of rest points and hidden attractor. We also exhibit that the new double-wing chaotic system has multi-stability and we illustrate the coexistence of attractors for two different sets of initial conditions. Some interesting dynamical properties such as offset boosting are also presented. Finally, we build an electronic circuit of the new chaotic system and show that the theoretical model has practical feasibility for implementation.

This paper investigates an attitude tracking maneuver problem for a rigid spacecraft with external disturbances, uncertain inertia parameters, actuator misalignments, and faults. First, all the uncertainty terms are split from the desired commanded control torque, and then, the nonsingular terminal sliding mode is implemented to design a fixed-time attitude tracking controller. Subsequently, an adaptive law is drawn into the attitude tracking controller to form a new control scheme, which eliminates the requirement of the upper bounds of all the uncertain terms. Besides, in the light of the concept of fixed-time stabilization, practical fixed-time convergence is achieved for attitude tracking errors. Finally, the numerical simulations are demonstrated to highlight the performance of the proposed controllers.

This paper realizes the independent complex route tracking based on the NAO robot hardware platform and an image processing technology. The camera captures an image and extracts a path through a series of image processes, such as threshold, filtering, and edge detection. The path recognition algorithms and its edge array were used to calculate these relative parameters that drive the anthropomorphic robot for complex route walking for autonomous tracking. These paths include the straight-route curves and the cross routes, which were identified by the different features accurately. Particularly, the slope-matching method is proposed to enable it to track in accordance with the established rules when meeting the cross routes. These methods separately calculate the slope from the intersection to paths in all directions, and then, the matching rate can be obtained by a predefined matching formula in terms of choosing the best path forward. All complex route tracking experiments were conducted by an anthropomorphic robot. The experimental results show that the robot imposed a strong anti-interference ability to filter out the noise and have accurate complex route tracking, which is significant for the anthropomorphic robot visual guide.

When a traditional mixture factor analysis (MFA) model is used for multimode process monitoring, the determination of parameter is complex, and the construction of monitoring statistics only considers the expectation in probability distributions of factor space and residual space. In this paper, a novel fault detection method based on a variational Bayesian MFA model for multimode process is introduced. The parameters of the MFA model structure, namely the number of local factor analyzer and the reduced dimensionality inside each factor analyzer, can be easily obtained through the birth-and-death Markov chain Monte Carlo algorithm and the variational inference technique. After parameter estimation for the Bayesian MFA model is done, a new monitoring index called negative variational log likelihood is developed by utilizing the whole information in probability distribution functions of all parameters. At last, two case studies, including a numerical example and the Tennessee Eastman (TE) process, verify the effectiveness and feasibility of the proposed monitoring scheme.

Graph embedding maps a graph into low-dimensional vectors, i.e., embedding matrix, while preserving the graph structure, solving the high computation and space cost for graph analysis. Matrix factorization (MF) is an effective means to achieve graph embedding since maintaining the utility of the graph structure. The personalized graph structure features implied in the embedding matrix can identify the individual, which potentially breaches individual sensitive information in the original graph. Currently, protecting individual privacy without compromising the utility is the key to sharing the embedding matrix. Differential privacy is a gold standard for publishing sensitive information while protecting privacy. The existing methods on differentially private MF, however, cannot be directly incorporated onto MF-based graph embedding as they undergo either high global sensitivity or iterative noise error accumulation, potentially rendering poor utility of MF-based graph embedding. To address the deficiency, this study proposes PPGD, a differentially private perturbed gradient descent method for MF-based graph embedding matrix sharing. Specifically, a Lipschitz condition on the objective function of the MF and a gradient clipping strategy are devised for bounding global sensitivity. Along the way, a scalable solution to global sensitivity that is independent on the original dataset is proposed. Further, a composite noise added means in the gradient descent is designed to guarantee privacy while enhancing the utility. The theoretical analysis shows that PPGD can generate processed embedding matrix with the utility maximization while achieving (ε, δ)-differential privacy. The experimental evaluations confirm the effectiveness and efficiency of PPGD.

In order to accurately detect the fuzzy anomaly data existing in big data networks, it is necessary to study the localization and recognition algorithm. The current algorithms have problems related to poor noise reduction, low recognition efficiency, high energy consumption and low accuracy. A novel localization and recognition algorithm for fuzzy anomaly data in big data networks is proposed. The multi-wavelet denoising method is used to remove the noise signals existing in the network. The k-means algorithm is utilized for network clustering, and the association mode between nodes and the unitary linearity regression model is adopted to eliminate spatially and temporally redundant data that exist in big data networks. The similarity anomaly detection method based on multi-feature aggregation identifies fuzzy anomaly data existing in big data networks, establishes an anomaly data localization model, and completes the localization and recognition of fuzzy anomaly data. Experimental results show that the proposed method has good noise reduction, high recognition efficiency, low energy consumption and high accuracy of localization and recognition.

This paper implements a novel line-following system for humanoid robots. Camera embedded on the robot’s head captures the image and then extracts the line using a high-speed and high-accuracy rectangular search method. This method divides the search location into three sides of rectangle and performs image convolution by edge detection matrix. The extracted line is used to calculate relative parameters, including forward velocity, lateral velocity and angular velocity that drive line-following walking. A proposed path curvature estimation method generates the forward velocity and guidance reference point of the robot. A classical PID controller and a PID controller with angle compensation are then used to set the lateral velocity and angular velocity of the robot, improving the performance in tracking a curved line. Line-following experiments for various shapes were conducted using humanoid robot NAO. Experimental results demonstrate the robot can follow different line shapes with the tracking error remaining at a low level. This is a significant improvement from existing biped robot visual navigation systems.