The normal data are sampled from the industrial process far more than fault data. Due to the existence of unbalanced data, the traditional learning method are difficult to classify the fault correctly. This paper designs a generation network to effectively augment the fault data and obtain the balanced industrial dataset. Conditional Generative Adversarial Network (CGAN) is constructed to generate a large amount of new fault data which has similar distribution with the original real fault data. The time series data are first transform into matrix format in order to adapt the input of CGAN. Then convolutional neural network (CNN) is used for fault diagnosis. The proposed method is applied in an actual gas-solid fluidized bed equipment to verify its effectiveness.

To address the challenge of multitarget parameters and non-stationary data streams in industrial data modeling, this paper proposes a multitarget online fuzzy stochastic configuration network (MOF-SCN) modeling method. The method consists of two parts: offline modeling and online optimization. The offline phase employs a multitarget sparse regularization strategy to enhance the learning mechanism of the fuzzy stochastic configuration network (F-SCN), improving the model's capacity to handle multitarget parameters. The online phase proposes two strategies, namely, a fuzzy rule growth and pruning strategy and an online optimization strategy for the enhancement layer of F-SCN, aimed at achieving real-time dynamic optimization of the model structure and parameters. This enhances the model's continual learning ability in non-stationary online data streams. Comparative experiments on two real-world industrial datasets demonstrate that the proposed method significantly outperforms in terms of adaptability and accuracy, thereby extending the applicability of F-SCN.

The idea of stacking layers is adopted to construct a deep multivariate statistical model, hierarchical canonical correlation analysis (HCCA). Its hierarchical structure is motivated form the deep network. The proposed HCCA model has the features of low computational complexity, strong correlative feature extraction, and causal interpretability. Its correlation advantages are theoretically demonstrated, then the evaluation metrics about accuracy and complexity are presented. The HCCA-based fault monitoring method is proposed for industrial processes, and the variable contributions are analyzed based on the residual statistic. The experiment results on Tennessee Eastman and real industry wastewater treatment processes show an average fault detection rate of 87.91$\%$and 99.49$\%$. It also decreases an average false alarm rate to 0.92$\%$and 0.32$\%$, respectively.

This article provides an efficient edge-end implementation solution for deep learning-based surface defect detection to improve the accuracy and efficiency when applied on edge devices with limited resource. An efficient you only look once (YOLO) network YOLOv5s-GhostNet is proposed, which highlights at the lightweight backbone/neck network, efficient feature extraction modules, and a fast learning scheme based on knowledge distillation. The parameter compression ratio is theoretically analyzed to show the decrease of computation complexity. The jointed loss is designed to enhance the generalization ability for new defects. An industrial testing platform with real-time edge-terminal-cloud detection system is developed with Raspberry Pi as edge. The experimental results show that the proposed method gets performances at complexity (floating-point operations per second (FLOPS) 8.2G, pt 7.9M), detection accuracy (precision 97.91$\%$, mean average precision (mAP) 96.66$\%$), efficiency [frames per second (FPS) 294 for single defect], and fast learning convergence (50 epochs). Compared to the existing methods, it reduces model size by 50$\%$on overage, increases the detection efficiency by 4 times and maintains the higher accuracy.

This article presents a novel physics-constrained zonotopic Kalman filter method for online capacity prediction of lithium-ion batteries. To describe capacity degradation, a state-space formulation is devised using the autoregressive model and an indirect representation of capacity. The approach consists of three steps: First, a zonotopic Kalman filter is proposed to estimate model parameters and parameter intervals. Subsequently, considering the capacity regeneration phenomenon, a physics-based constraint term is presented to optimize parameters, which updates the estimated model parameters obtained by the zonotopic Kalman filter. Finally, parameters and interval estimation are utilized to predict the future short-term capacity. The case study demonstrates the validity of our approach. Moreover, comparisons with the ellipsoid-based extended Kalman filter and predictive maintenance toolbox suggest that our approach can obtain more precise capacity prediction and tighter capacity interval results.

In the field of autonomous driving and specific environments, target detection is a critical task module. Currently, the mainstream approach to target detection is to use deep learning to train specific network models, enabling them to recognize targets. Although many effective network models have been proposed by scholars, there are few target detection networks tailored for low-light environments. In practical applications, complex lighting changes can lead to decreased accuracy in target detection. This paper combines a low-light enhancement network with a LiDAR-camera fusion target detection network to achieve target detection in low-light environments and validates the algorithm using the Nuscenes benchmark dataset. The experimental results demonstrate that the improved network exhibits greater robustness in target detection under complex lighting conditions.

The paper proposes a distributed multi-robot cooperative hunting method in cluttered environments with guaranteed collision avoidance. First, to achieve collision avoidance, a robot safety region collision avoidance method based on Buffered Voronoi Cells (BVC) is proposed. Then, under the BVC collision avoidance framework, a Kalman filer is designed to estimate the evader' position. Next, a hunting cost function based on the evader's position probability density function is constructed. Furthermore, the hunting controller for the pursuers is designed inspired by Voronoi coverage control. Finally, simulation results demonstrate that under the influence of this controller, the distance between the pursuers and the evader continuously decreases until the hunting is successful.

This paper proposes an improved semantic segmentation model based on Fully Convolutional Network(FCN). Firstly, this paper integrates the channel attention module into the backbone of FCN to identify the channels that are more important for semantic segmentation. Secondly, this paper adds a multi-scale feature fusion module to the network to integrate multi-scale feature information. Thirdly, this paper replaces some of standard convolutions in the backbone network with dilated convolutions to increase the receptive field. Experimental results demonstrate that after adding the two modules, the pixel accuracy can reach 75.8%, and the mIOU value has increased by 2.8% compared to the original FCN model. Moreover, utilizing pre-trained weights during the training process can greatly enhance the performance of the model.

This paper proposes a flexible job-shop scheduling problem optimization method, which focuses on providing solutions for industrial production. First, in terms of model construction, the method further considers the cost of automated guided vehicles and the priority of workpiece production based on previous methods. Then, this method solves the model by non-dominated sorting genetic algorithm with self-cross and delete-mutation. It reduces the production time and energy by an average of 6.4% and 19.4%, which are 5.4% and 15.1% with the priority. Finally, the simulation verifies that the method effectively reduces the production cost while realizing the adjustment of the automated guided vehicle number and the workpiece production sequence.

This article investigates a class of multiobjective optimization fault detection observer design problems for linear parameter varying (LPV) systems considering the unknown but bounded disturbance with an adaptive event-triggered scheme. In this study, the actuator faults are considered in the low-frequency domain. First, to save the communication bandwidth and improve communication efficiency, an adaptively adjusted event-triggered (AAET) mechanism is proposed. Then, in order to make the designed observer gain satisfy both fault sensitivity and disturbance robust conditions, an$H_{-}/L_{\infty }$multiobjective optimization problem is proposed and solved by appropriate linear matrix inequalities. Next, the upper and lower bounds of the generated residual are calculated by the zonotope method when considering the estimation uncertainty. Fault detection can be achieved by judging whether the zero value belongs to the generated range of the residual signal. Finally, a simulation case is used to verify the effectiveness of the proposed method.

This paper investigates a finite-frequency H-/H∞fault detection method for discrete-time T-S fuzzy systems with unmeasurable premise variables. To minimize the effect of uncertainties on system performance and maximize that of actuator faults on the generated residual, both the H∞disturbance attenuation index and finite-frequency H-fault sensitivity index are utilized. Since the premised variables are unmeasurable, the existing generalized Kalman-Yakubovich-Popov lemma cannot be directly extended to these nonlinear systems. In this paper, the conditions of allowing one to design the proposed H-/H∞fault detection observer are established and transformed into linear matrix inequalities. Some scalars and slack matrices are introduced to bring extra degrees of freedom in observer design. Finally, a single-link robotic manipulator model is utilized to illustrate that the proposed technique can detect faults with smaller amplitude than that required by a normal H∞observer technique.

This paper presents a novel interval fault estimation approach by using zonotope technique for discrete-time linear parameter-varying systems in the presence of bounded parametric uncertainties, measured perturbation, and system disturbance. First, an augmented descriptor system is generated by using augmentation technique. Thus, the problem of interval fault estimation is transformed into the interval augmented state estimation. Then, an outer approximation of the new augmented state estimation domain is computed by using zonotope method. A zonotope should be consistent with the given outputs, perturbation, disturbance, and parametric uncertainties. Besides, it is minimized at each sampled time via an analytic formulation. Finally, a vehicle lateral dynamic nonlinear model is utilized to show the feasibility and effectiveness of the proposed zonotopic fault estimation technique.