Search

Data Availability Statement: The data that support the findings of this study are available from the corresponding author upon reasonable request. The Deanship of Scientific Research (DSR) at King Abdulaziz University, Jeddah, Saudi Arabia (Grant no. (FP-093-43)); National Natural Science Foundation of China under Grants 61773156, 61873148, and 61933007; Natural Science Foundation of Henan Province of China under Grant 202300410159; Program for Science and Technology Innovation Talents in the Universities of Henan Province of China under Grant 19HASTIT028; Royal Society of the U.K.; Alexander von Humboldt Foundation of Germany.

In the production process of lithium battery, the quality inspection requirements of lithium battery are very high. At present, most of the work is done manually. Aiming at the problem of large manual inspection workload and large error, the robot visual inspection technology is applied to the production of lithium battery. In recent years, with the rapid development and progress of science and technology, the rapid development of visual detection hardware and algorithms, making it possible to screen defective products through visual detection algorithms. This paper takes lithium battery as the research object, and studies its vision detection algorithm. As a common commodity, the quality of lithium battery is the key for users to choose. With the increasing requirements of users for battery quality, how to produce high-quality battery is the key problem to be solved by manufacturers. However, at present, the defects of battery surface are mostly carried out manually. There are low efficiency and low detection rate in the process of manual detection. In this paper, the visual detection algorithm is studied to detect the defects such as pits, rust marks and broken skin on the surface of lithium battery, specifically to design the imaging experimental platform of lithium battery; use different lighting schemes to design different battery positioning and extraction algorithms; use Hough detection method to locate the battery surface, and design the battery defect algorithm for this, and compare the algorithm through experiments.

The purpose of knowledge graph entity disambiguation is to match the ambiguous entities to the corresponding entities in the knowledge graph. Current entity ambiguity elimination methods usually use the context information of the entity and its attributes to obtain the mention embedding vector, compare it with the candidate entity embedding vector for similarity, and perform entity matching through the similarity. The disadvantage of this type of method is that it ignores the structural characteristics of the knowledge graph where the entity is located, that is, the connection between the entity and the entity, and therefore cannot obtain the global semantic features of the entity. To improve the Precision and Recall of entity disambiguation problems, we propose the EDEGE (Entity Disambiguation based on Entity and Graph Embedding) method, which utilizes the semantic embedding vector of entity relationship and the embedding vector of subgraph structure feature. EDEGE first trains the semantic vector of the entity relationship, then trains the graph structure vector of the subgraph where the entity is located, and balances the weights of these two vectors through the entity similarity function. Finally, the balanced vector is input into the graph neural network, and the matching between the entities is output to achieve entity disambiguation. Extensive experimental results proved the effectiveness of the proposed method. Among them, on the ACE2004 data set, the Precision, Recall, and F1 values of EDEGE are 9.2%, 7%, and 11.2% higher than baseline methods.

This paper is concerned with the exponential synchronization problem for chaotic neural networks with discrete and distributed delays under input saturations. Attention is focused on the design of saturated feedback controller such that the synchronization error system is locally exponentially stable. Based on delay-dependent sector conditions and augmented Lyapunov–Krasovskii functionals, sufficient conditions are established in the framework of linear matrix inequalities. Moreover, the optimization problems are proposed to maximize the estimate of the domain of attraction. Finally, two simulation examples show the effectiveness and benefit of the obtained results.

This proposal considers the issue of L 2 - L ∞ state estimation for delayed neural networks. A novel Lyapunov-Krasovskii functional is constructed, which contains augmented s-dependent integral and multiple integral terms. Then, in order to cooperate with the constructed Lyapunov-Krasovskii functional effectively to reduce the conservatism of the result, generalized free-weighting-matrix integral inequality and convex combination method are utilized. Meanwhile, multiple integral terms containing triple integral are utilized when analyzing the L 2 - L ∞ performance. As a result, novel delay-dependent conditions are obtained, which can guarantee that the delayed neural network is asymptotically stable with desired performance level. Finally, the given numerical examples show the superiority of the proposed approach.

Image segmentation is one of the most important assignments in computer vision. In this paper, we present an unsupervised segmentation method that combines graph-based clustering and high-level semantic features. We over-segment the given image into a collection of superpixels. Various low-level features assemble a descriptor of each superpixel. Besides the intrinsic image features such as color, texture and gradient, we add image saliency into the low-level visual features as prior knowledge of human perception. Instead of using the low-level features directly, we design a graph-based method to segment the image by clustering the high-level semantic features learned from a neural network. We test the proposed method on two well-known datasets. The experimental evaluation validates that our approach can provide consistent and meaningful segmentation.

This work investigates L2-L∞ filtering problem for a class of stochastic systems with time-delay and randomly occurring phenomena. The purpose of the addressed problem is to design a full order fil...

In this paper, the time-delayed anti-windup problem is addressed for linear input-delay systems with actuator saturations. By using an augmented Lyapunov-Krasovskii functional, the generalized sector condition and some advanced inequalities, anti-windup synthesis conditions are first established by means of linear matrix inequalities. In particular, the first time-interval is considered in determining the performances of closed-loop systems under a relatively practical control setting. Then, several optimization problems are proposed to solve the optimal performance indices. Finally, a simulation example is given to illustrate the effectiveness of the proposed anti-windup strategy.

Network is a powerful language to represent relational data. One way to understand network is to analyze groups of nodes which share same properties or functions. The task of discovering such groups is known as community detection. The community detection in real-life networks, the majority of which are weighted temporal text networks, is confronted with two main problems - how to model the weight of edges and how to exploit the temporal information. Existing works either ignore the edge weight or utilize it in graph measures like modularity, which lacks scalability. And currently the common-used method involving temporal information is to discretize the time, which leads to series of problems. We are thus motivated to present a new method to encode the edge weight and temporal information. A probabilistic generative model, named Custom Temporal Community Detection (CTCD) is introduced, which views the link between two nodes as a weighted edge with several time stamps. Our model utilizes network, semantic and temporal information simultaneously to extract temporal community affiliations for individual user, influence strength across communities and temporal interested topic in each community. An efficient inference method, which scales linearly, and corresponding parallel implementation are proposed to adapt to large datasets. Through the knowledge extracted by CTCD, we are able to spot the community shift of the individual user, to which little attention has been given, and employ it to track the development of the communities over time. Moreover, experiments on two large-scale weighted temporal text networks show that CTCD gains significant improvement over state-of-the-art methods on a series of tasks.

This paper is concerned with the robust $$H_\infty $$ filtering problem for a class of discrete-time systems with polytopic uncertainties and multiple time delays. Different from the most existing techniques, the novel augmented Lyapunov–Krasovskii functionals are constructed by incorporating the relationships between multiple time delays. Based on the proposed functionals and the Wirtinger-based inequality, sufficient conditions are first established under which the filtering error system is asymptotically stable and has an prescribed $$H_\infty $$ performance level. Then, the adjusting parameters are introduced such that the filter gains can be effectively obtained by solving certain linear matrix inequalities. Finally, two numerical examples are given to demonstrate the effectiveness and the benefit of the proposed approach.

As a relatively new swarm intelligence algorithm, the fireworks algorithm (FWA) has been applied to solve lots of real-world optimization problem. However, there are still some shortcomings in the FWA algorithms. The search equation of FWA is relatively simple. Since the search mechanism of FWA mainly relies on the explosion sparks, the exploration and exploitation abilities of the algorithm are limited. In order to improve the performance of FWA, a simplified hybrid fireworks algorithm (SHFWA) is proposed in this paper. In SHFWA, to enhance the exploitation ability, a modified search formula is designed for core firework swarm. To enhance the exploration ability, for each firework swarm, another way of generating sparks–harmony spark is designed. In the conventional fireworks algorithm, the calculation of the number of sparks generated by each firework and the calculation of amplitude of explosion for each firework are very complex. In SHFWA, a simplified method is employed to compute these two variables. By introducing these methods, SHFWA is easy to implement and is good at exploration and exploitation. The proposed algorithm is tested on 40 benchmark functions. The experimental results demonstrate that SHFWA performs effectively and competitively when compared with several reported algorithms.

SummaryEstimating the robot state within a known map is an essential problem for mobile robot; it is also referred to “localization”. Even LiDAR-based localization is practical in many applications, it is difficult to achieve global localization with LiDAR only for its low-dimension feedback, especially in environments with repetitive geometric features. A sensor-fusion-based localization system is introduced in this paper, which has the capability of addressing the global localization problem. Both LiDAR and vision sensors are integrated, making use of the rich information introduced by vision sensor and the robustness from LiDAR. A hybrid grid-map is built for global localization, and a visual global descriptor is applied to speed up the localization convergence, combined with a pose refining pipeline for improving the localization accuracy. Also, a trigger mechanism is introduced to solve kidnapped problem and verify the relocalization result. The experiments under different conditions are designed to evaluate the performance of the proposed approach, as well as a comparison with the existing localization systems. According to the experimental results, our system is able to solve the global localization problem, and the sensor-fusion mechanism in our system has an improved performance.

In this paper, the local stabilization problem is dealt with for a class of continuous-time multiple input-delay systems subject to saturating actuators. Novel sector conditions are first proposed that take both delayed and current states into account, thereby reducing potential conservatism. Then, by using the piecewise Lyapunov-like functional and carrying out rigorous mathematical deduction, a sufficient condition is established under which the closed-loop dynamics is exponentially stable for admissible initial conditions. Subsequently, the explicit characterization of controller gains is obtained in terms of the solvability of linear matrix inequalities. The special cases concerning the constant and single delays are also discussed. Moreover, optimization problems are put forward to maximize the estimate of the domain of attraction. Finally, two simulation examples are presented to illustrate the effectiveness and advantages of the obtained results.

This paper aims at optimizing the housing assignment of warehouse breeding. A model of the housing assignment for minimizing the total completion time of feeding in cycle of slaughter is established, and a Gaussian social spider algorithm (GSSO) is proposed. By introducing the subpopulation reconstruction mechanism, Gaussian mating radius and multi-mating operator, GSSO can balance the global exploration and the local exploitation. Simulation results demonstrate that compared with other algorithms, the proposed algorithm achieves higher accuracy and quicker convergence, meanwhile obtains a more satisfactory solution in a shorter period of time.

Robustness in visual odometry (VO) systems is critical, as it determines reliable performance in various scenarios and challenging environments. Especially with the development of data-driven technology, such as deep learning, the combination of data-driven VO and traditional model-based VO has achieved accurate tracking performance. However, the existence of local optimums in the model-based cost function still limits the robustness. In this study, we introduce a novel framework with a particle filter (PF) in the optimization process, where the PF is constructed by deep neural network (DNN) prediction. We propose constructing the PF by motion prediction classification and its uncertainty based on the characteristic of on-road driving motion. At the same time, an interval DNN prediction strategy is introduced to improve the real-time performance. Experimental results show that our framework obtains better tracking accuracy and robustness than the existing works, while the time consumption is maintained.

This paper deals with the L2–L∞ state estimation for neural networks with time-varying delays. Considering the limited channel capacity or the long transmission time during signal transmission, a new system model with different state and measurement time-varying delays is established. Then, a new Lyapunov–Krasovskii functional (LKF) taking advantage of two types of delay information is constructed, Jensen integral inequality, Wirtinger-based integral inequality and convex combination approach are used to estimate the derivative of functional. Meantime, a novel L2–L∞ performance analysis method making full use of delay information is proposed, as a result, the delay-dependent conditions with less conservatism are obtained, under which the estimation error system is asymptotically stable with a prescribed L2–L∞ performance level. Numerical examples are given to show the effectiveness and the advantage of the proposed method.

This article is concerned with the local stabilization problem for discrete-time systems with both distributed state delay and fast-varying input delay under actuator saturations. By introducing some terms concerning the distributedly delayed state and the current state, a novel polytopic model is first proposed to characterize the delayed saturation nonlinearity. Then, by incorporating a piecewise Lyapunov functional and some summation inequalities, a sufficient condition is established by means of linear matrix inequalities under which the closed-loop system is locally exponentially stable. Moreover, the conditions for two special cases with single state delay and single input delay are proposed. Subsequently, certain optimization problems are formulated with aim to maximize the estimate of the region of attraction. Finally, two examples show the effectiveness and values of the obtained results.

In this paper, for multiple different chaotic systems with fully unknown parameters, a novel synchronization scheme called ‘modified function projective multi-lag generalized compound synchronization’ is put forward. As an advantage of the new method, not only the addition and subtraction, but also the multiplication of multiple chaotic systems are taken into consideration. This makes the signal hidden channels more abundant and the signal hidden methods more flexible. By virtue of finite-time stability theory and an adaptive control technique, a finite-time adaptive control scheme is established to realize the finite-time synchronization and to properly evaluate the unknown parameters. A detailed theoretical derivation and a specific numerical simulation demonstrate the feasibility and validity of the advanced scheme.

This paper is concerned with the analysis problem for the globally asymptotic stability of a class of stochastic neural networks with finite or infinite distributed delays. By using the delay decomposition idea, a novel augmented Lyapunov–Krasovskii functional containing double and triple integral terms is constructed, based on which and in combination with the Jensen integral inequalities, a less conservative stability condition is established for stochastic neural networks with infinite distributed delay by means of linear matrix inequalities. As for stochastic neural networks with finite distributed delay, the Wirtinger-based integral inequality is further introduced, together with the augmented Lyapunov–Krasovskii functional, to obtain a more effective stability condition. Finally, several numerical examples demonstrate that our proposed conditions improve typical existing ones.

In this paper, the networked synchronization communication for nonlinear uncertain fractional-order chaotic systems is investigated. Notice that the network transmission capacity is limited, a novel combination event-triggered mechanism is designed. Based on the fractional Lyapunov stability criterion and adaptive control technique, an event-triggered adaptive controller is constructed and a sufficient networked synchronization condition for the above-mentioned fractional-order chaotic systems with uncertainties and disturbances is attained. The detailed theoretical derivation and specific numerical simulation demonstrate that the proposed networked synchronization strategy can reduce the burden of network bandwidth effectively without losing the desired synchronization performance. Meanwhile, Zeno phenomenon is excluded.

A particle swarm optimization algorithm with crossover operation (PSOCO) is proposed. In the proposed PSOCO, two different crossover operations are employed in order to breed promising exemplars. By performing crossover on the personal historical best position of each particle, the effective guiding exemplars are constructed and they maintain a good diversity. In turn, these high quality exemplars are used to guide the evolution of particles. PSOCO is two-layer particle swarm optimization with positive feedback mechanism. In order to test the performance of PSOCO, we use a set of widely used benchmark functions. The experimental results demonstrate that the proposed PSOCO is a competitive optimizer in terms of both solution quality and efficiency.

Because different optimization algorithms have different search behaviors and advantages, hybrid strategy is one of the main research directions to improve the performance of PSO. Inspired by this idea, a dynamic multi-swarm differential learning particle swarm optimizer (DMSDL-PSO) is proposed in this paper. We propose a novel method to merge the differential evolution operator into each sub-swarm of the DMSDL-PSO. Combining the exploration capability of the differential mutation and employing Quasi-Newton method as a local searcher to enhance the exploitation capability, DMSDL-PSO has a good exploration and exploitation capability. According to the characteristics of the DMSDL-PSO, three modified differential mutation operators are discussed. Differential mutation is adopted for the personal historically best particle. Because the velocity updating equation of the particles in PSO has some shortcomings, a modified velocity updating equation is adopted in DMSDL-PSO. In DMSDL-PSO, in which the particles are divided into several small and dynamic sub-swarms. The dynamic change of sub-swarms can promote the information exchange of the whole swarm. In order to test the performance of DMSDL-PSO, 41 benchmark functions are adopted. Lots of numerical experiments are conducted to compare DMSDL-PSO with other popular algorithms. The numerical results demonstrate that DMSDL-PSO performs better on some benchmark functions.

This paper is concerned with the finite-time $ H_\infty $ control problem for a chaotic finance system subject to energy-bounded external disturbance via delayed feedback controller. Based on an augmented Lyapunov-like functional, the Wirtinger-based inequality and the novel finite-time boundedness analysis approach, a delay-dependent sufficient condition is proposed in terms of linear matrix inequalities such that the closed-loop error system is finite-time bounded with a prescribed $ H_\infty $ performance level. By simple modification, the sufficient condition based on the standard $ H_\infty $ control design is also obtained. Finally, simulation results are given to demonstrate the effectiveness and advantages of our proposed results.

In this article, a particle swarm optimization algorithm with two differential mutation (PSOTD) is proposed. In PSOTD, a novel structure with two swarms and two layers (bottom layer and top layer) is designed. The top layer consists of all the personal best particles, and the bottom layer consists of all the particles. We divide the particles in the top layer into two sub-swarms. Two different differential mutation operations with two different control parameters are employed in order to breed the particles in the top layer. Thus, one sub-swarm has a good exploration capability, and the other sub-swarm has a good exploitation capability. Obviously, since the top layer leads the bottom layer, the bottom particles achieve a good trade-off between exploration and exploitation. Under the searching structure, PSO enhances the global search capability and search efficiency. In order to test the performance of PSOTD, 44 benchmark functions widely adopted in the literature are used. The experimental results demonstrate that the proposed PSOTD outperforms most of the other tested variants of the PSO in terms of both solution quality and efficiency.

This paper is concerned with the passivity problem for neural networks with leakage delay and time-varying transmission delay. Using some novel Lyapunov-Krasovskii (L-K) functionals, and combining with the Wirtinger integral inequality, some less conservative delay-dependent passivity conditions are proposed in terms of linear matrix inequalities (LMIs). Different from the existing approaches, the model transformation is abandoned in this paper, and the proposed L-K functionals incorporate the interconnected terms related to both the leakage delay and the time-varying delay. Numerical examples show that the obtained conditions are less conservative.

The DEM generalization is the foundation of expressing and analyzing the terrain and the basis of multi-scale observation. Meanwhile, it is also the core of building the multi-scale geographic database. This paper would like to propose a new algorithm using profile simplification in four directions(4-DP). This algorithm is composed of two parts, namely extraction of terrain feature points in local window as well as in global profile line and reconstruction of DEMs. The paper used the 5 m resolution DEM of the Suide in Loess Plateau of China as the original data. In the experiment, this paper has achieved the generalized DEM with 5 m and 25 m resolution by removed small details and computed out the optimal threshold. In contrast to the classic algorithms, VIP and Aggregate, based on three evaluation methods. The results show that this method is able to retain the main geographical information effectively in terrain surface.

In recent years, with the aggravation of environmental pollution, relying on the traditional detection of environmental pollution has been unable to meet the current requirements for the environment, the use of advanced technology to detect environmental pollution has become crucial. In order to meet the requirements of today's era, with the rapid development of image recognition technology, it is necessary to study how to apply it to environmental pollution detection. The image recognition technology based on embedded technology has the characteristics of high discrimination, high acceptability and strong touch sense. It is of great significance for environmental monitoring to make full use of image recognition technology. Image recognition technology is to capture the same environment by digital camera, and then store the obtained image by computer. The HSI model is used to quantify the stored photos, and the variance of the gradient function is used to form photos and images with different levels of clarity, so as to analyze the environmental pollution according to the quantified results. In this paper, the ambient air quality is taken as the research object, and HSI model is used to quantify, so as to analyze the correlation of air detection results.

Over the past two decades, the synchronization problem for dynamical networks has drawn significant attention due to its clear practical insight in biological systems, social networks, and neuroscience. In the case where a dynamical network cannot achieve the synchronization by itself, the feedback controller should be added to drive the network toward a desired orbit. On the other hand, the time delays may often occur in the nodes or the couplings of a dynamical network, and the existence of time delays may induce some undesirable dynamics or even instability. Moreover, in the course of implementing a feedback controller, the inevitable actuator limitations could downgrade the system performance and, in the worst case, destabilize the closed-loop dynamics. The main purpose of this paper is to consider the synchronization problem for a class of delayed dynamical networks with actuator saturations. Each node of the dynamical network is described by a nonlinear system with a time-varying delay and the intermittent control strategy is proposed. By using a combination of novel sector conditions, piecewise Lyapunov-like functionals and the switched system approach, delay-dependent sufficient conditions are first obtained under which the dynamical network is locally exponentially synchronized. Then, the explicit characterization of the controller gains is established by means of the feasibility of certain matrix inequalities. Furthermore, optimization problems are formulated in order to acquire a larger estimate of the set of initial conditions for the evolution of the error dynamics when designing the intermittent controller. Finally, two examples are given to show the benefits and effectiveness of the developed theoretical results.

This paper is concerned with the stabilization and l 2 gain control problems for a class of networked control systems with actuator saturation. By using the switched system model, the regional stabilization condition is firstly obtained. Then, the corresponding optimization problem is given to maximize the estimate of the domain of attraction. Under zero initial condition, the state feedback controller is also designed under which the l 2 gain from disturbances to the controlled output is less than a given positive scalar. As the further discussion, the improved stabilization condition is proposed by exploring a more relaxed inequality. Finally, a simulation example is given to illustrate the effectiveness and values of the obtained results in this paper.

Many practical control systems can be modeled as switched linear systems with stabilizable and unstabilizable subsystems. In this paper, control synthesis for such a class of systems with actuator saturation is well investigated in the continuous-time and discrete-time cases. Based on the time-dependent switching signals and multiple Lyapunov function method, stabilization conditions are established in terms of LMIs. To obtain an attractive region as large as possible, the optimization problems are formulated. As the applications, the asynchronously switched control and intermittent control under actuator saturation are discussed. Numerical examples and simulations are presented to illustrate the feasibility and values of the proposed results.

The DEM generalization is the basis of multi-dimensional observation, the basis of expressing and analyzing the terrain. DEM is also the core of building the Multi-Scale Geographic Database. Thus, many researchers have studied both the theory and the method of DEM generalization. This paper proposed a new method of generalizing terrain, which extracts feature points based on the tree model construction which considering the nested relationship of watershed characteristics. The paper used the 5 m resolution DEM of the Jiuyuan gully watersheds in the Loess Plateau as the original data and extracted the feature points in every single watershed to reconstruct the DEM. The paper has achieved generalization from 1:10000 DEM to 1:50000 DEM by computing the best threshold. The best threshold is 0.06. In the last part of the paper, the height accuracy of the generalized DEM is analyzed by comparing it with some other classic methods, such as aggregation, resample, and VIP based on the original 1:50000 DEM. The outcome shows that the method performed well. The method can choose the best threshold according to the target generalization scale to decide the density of the feature points in the watershed. Meanwhile, this method can reserve the skeleton of the terrain, which can meet the needs of different levels of generalization. Additionally, through overlapped contour contrast, elevation statistical parameters and slope and aspect analysis, we found out that the W8D algorithm performed well and effectively in terrain representation.

The essay probes into the present problems of the measurement errors caused by harmonic interference in the electric monitoring equipment for underground coal mine. We applied three-phase watt-hour meter in view of FFT(Fast Fourier Transformation) algorithm based on Industrial Ethernet, which can effectively analyze the harmonic component of the voltage and the current from the field. This can accurately calculate the electrical parameters of electrical equipment, improving the quality of electricity and achieving optimal energy management of coal mine.

The model and the normal control method of the cascaded H-bridge active power filter is described firstly in this paper. However, problems exist in the normal control. One of the main problems is the unbalance of DC capacitor voltages of the H-bridge units. In this paper, an improved method for DC capacitor voltages control of the cascaded H-bridge active power filter is presented. With slightly shifting the modulation waves, it makes the DC capacitor voltages balancing in the accepted tolerance without any additional units. The method is validated by simulation and experiment.

Supplier selection decisions are usually made by multiple decision makers according to multiple criteria. A method combining the technique for preference by similarity to ideal solution (TOPSIS) and 0-1 programming was proposed for supplier selection in supply chain management. First, the priority orders of suppliers under each criteria given by individual decision makers were aggregated to the ranking orders in the group's view by TOPSIS considering weights of decision makers. Then, the final integrated ranking orders of all suppliers were derived from the group's priority orders of them with respect to each criteria by 0-1 programming. A numerical example was presented to demonstrate the application of the proposed method and the comparisons of the results have shown the method is effective.

The model and the normal control method of the cascaded H-bridge active power filter is described firstly in this paper. However, problems exist in the normal control. One of the main problems is the unbalance of dc capacitor voltages of the H-bridge units. In this paper, an improved method for dc capacitor voltages control of the cascaded H-bridge active power filter is presented. With slightly shifting the modulation waves, it makes the dc capacitor voltages balancing in the accepted tolerance without any additional units. The method is validated by simulation.

This paper presents a new and open Web Service-Based DSS framework under distributed service-oriented architecture. In the past, DSS always refers to a software product. But in this new framework, DSS appears as a website, we called it as decision support website. This paper explores the details of the architecture of the decision support website and describes the business mode about this website. Then we give the whole implementation process of web service. The new DSS change the features of the traditional DSS completely by adopting web service application integration technology and introducing into new business mode.