Deep learning is currently the mainstream method for ceramic defect detection, and it requires a large number of defect samples to train the network. However, collecting these defect samples is very time-consuming and...
详细信息
Deep learning is currently the mainstream method for ceramic defect detection, and it requires a large number of defect samples to train the network. However, collecting these defect samples is very time-consuming and deep learning suffers from few-shot learning problems. In this study, a StyleGAN3-based data augmentation method for ceramic defect detection was proposed which can generate ceramic defect samples and thus reduce the data collection work. Experiments show that our method uses less training time, has a more stable training process, and can improve the accuracy of the detection network.
The surface defects of ceramic tile greatly affect the service life of ceramic tile. At present, many detection methods of ceramic tile surface defects are mostly used for ceramic tiles with monochrome background or s...
The surface defects of ceramic tile greatly affect the service life of ceramic tile. At present, many detection methods of ceramic tile surface defects are mostly used for ceramic tiles with monochrome background or simple texture. However, many tiles with complex and irregular surface patterns are used in practical applications, but many methods cannot effectively detect surface defects in such tiles. This paper presents a double input feature difference network structure to overcome the limitation. First, a double input channel is constructed to extract features from the template image and the defect image respectively. Next, a method of feature difference is performed at different depths to suppress the background interference and prevent misclassification between different defect categories. Then a parameter-free attention module is embedded in the backbone to improve the ability of feature extraction. Experimental results show that this model effectively improves the mean average accuracy of 8.3% and the recall rate of 11.7%.
In recent years, quadratic optimizations have become increasingly popular in engineering. However, conventional methods that investigate this problem from the perspective of a canonical form with linear constraints ar...
In recent years, quadratic optimizations have become increasingly popular in engineering. However, conventional methods that investigate this problem from the perspective of a canonical form with linear constraints are not effective in dealing with the significant challenges posed by quadratic constraints in practice. This paper proposes a solution framework for the quadratic optimization with quadratic constraints (QOQC) based on innovative artificial societies, computational experiments, and parallel execution (ACP) framework. Then, a gradient projection differential neural solution (GPDNS) is proposed to address this. To illustrate the effectiveness of the GPDNS model in solving the QOQC system, numerical simulations are provided. Overall, this paper presents the potential of innovative approaches like the ACP framework to enhance our capabilities in addressing challenging optimization systems.
Geo-hazards have become one of the main disasters endangering the safety of people's lives and property in the world. In order to improve the early warning of disasters, a persistent monitoring method of multi-age...
Geo-hazards have become one of the main disasters endangering the safety of people's lives and property in the world. In order to improve the early warning of disasters, a persistent monitoring method of multi-agent systems is proposed in this work. To ensure that the agent's energy is never exhausted, the set invariance constraint is included in the optimization problem. The goal is to minimize the difference between the actual control input of the robot and the nominal control input corresponding to the task to be performed. Moreover, the control barrier function (CBF) is used to transform the forward invariance of a subset of the robot state space into a control input constraint. The coverage control method in an uncertain environment is verified by numerical simulation. This work provides new insights into effective monitoring and early warning of geo-hazards.
A fault diagnosis method based on Discrete Hidden Markov Models is proposed in this paper to identify the fault causing alarm flood sequences. The proposed method consists of the following steps: First, the alarm floo...
A fault diagnosis method based on Discrete Hidden Markov Models is proposed in this paper to identify the fault causing alarm flood sequences. The proposed method consists of the following steps: First, the alarm flood data is pre-processed to ensure that all sequences are of uniform length, and a separate Discrete Hidden Markov model is trained for each fault to capture the relationship between the fault and the alarm sequences. Second, given an observation sequence, the log-likelihood probability values under different Discrete Hidden Markov models are calculated and the maximum probability is selected to determine the type of corresponding fault. Last, the feasibility of the proposed method is verified by simulation data obtained from a public industrial model. The results show that the method can effectively identify the faults that trigger alarm floods.
Leaks in natural gas pipelines can cause very serious safety accidents, and timely detection and remedial action can greatly reduce the losses. In recent years, pipeline leak detection has received extensive studies. ...
Leaks in natural gas pipelines can cause very serious safety accidents, and timely detection and remedial action can greatly reduce the losses. In recent years, pipeline leak detection has received extensive studies. Most methods use pressure sensors or acoustic sensors to detect pipelines, but there are certain limitations on the usage scenarios and detection time delays. On this basis, this paper selects maglev vibration detector to detect the vibration signal of pipelines. The difficulty lies in that, sudden changes in vibration signals due to external disturbances, may lead to false alarms. Therefore, this paper proposes a pipeline leak detection method using Multivariate Gaussian Distribution based Kullback-Leibler Divergence (MGD-KLD) and on-delay timer to reduce false alarms during the detection process. In this paper, by constructing a simulated pipeline platform for leak experiments and applying the above method to process the experimental data, the false alarm rate of pipeline leak detection can be effectively reduced.
Establishing the dynamics model of the offshore drilling experimental system can better complete the offshore drilling test in the laboratory environment and reduce the cost of testing.A dynamical modeling method for ...
Establishing the dynamics model of the offshore drilling experimental system can better complete the offshore drilling test in the laboratory environment and reduce the cost of testing.A dynamical modeling method for the offshore drilling experimental system built on the double-layer Stewart parallel mechanism is ***,the kinematic and dynamical characteristics of the double-layer Stewart parallel mechanism are combined with the Lagrange method and the virtual work method to establish the dynamics model of the *** a parameter identification scheme is designed using a nonlinear gray system estimation method based on the trust-domain reflection algorithm,and the model parameters are *** model is downscaled to improve the feasibility of the identification scheme and the accuracy of the identified *** actual experimental system data verify this model's correctness and the model parameters' accuracy.
For hybrid energy storage systems in DC microgrids, a droop control consisting of virtual capacitors and virtual resistors can decompose power into high-frequency components and low-frequency components, then assign t...
For hybrid energy storage systems in DC microgrids, a droop control consisting of virtual capacitors and virtual resistors can decompose power into high-frequency components and low-frequency components, then assign them to batteries and supercapacitors to respond respectively. However, aiming at the service life of the energy storage system, this paper considers the characteristics and key parameters of the hybrid energy storage structure and proposes an adaptive drooping comprehensive control strategy considering the SOC of the energy storage unit given the shortcomings of power distribution within the current hybrid energy storage. According to the self-regulation capacity of each energy storage unit, it is sorted and constrained, and protected by using SOC, which ensures the economy and safety of the system while ensuring power distribution. The traditional droop control and adaptive droop control are simulated to verify the effectiveness of the proposed control strategy.
This paper addresses the robust finite-time stabi-lization (FTS) issue for stochastic parabolic PDE systems via non-fragile spatial sampled-data control scheme. First, a class of distributed parameter systems characte...
This paper addresses the robust finite-time stabi-lization (FTS) issue for stochastic parabolic PDE systems via non-fragile spatial sampled-data control scheme. First, a class of distributed parameter systems characterized by the delayed stochastic parabolic partial differential equation is developed for analyzing the effects of stochastic disturbance, structural uncertainty, and discrete delay on the system performance. Then, a non-fragile spatial sampled-data control scheme is established by setting sampling points in the spatial domain, which effectively saves communication resources and ensures that the closed-loop system maintains good performance when the controller is perturbed. Moreover, based on the partial differential equation theory, stochastic analysis approach, and the extended Wirtinger's inequality technique, several criteria are provided to ensure the robust FTS of stochastic parabolic PDE systems in the mean square sense. Lastly, a numerical example is provided to verify the feasibility of the suggested stabilization criteria and control scheme.
At present, most research on the coverage of multi-agent systems is based on Euclidean distance. This does not consider the existence of obstacles and has great limitations in the application. In this paper, a kind of...
At present, most research on the coverage of multi-agent systems is based on Euclidean distance. This does not consider the existence of obstacles and has great limitations in the application. In this paper, a kind of coverage control problem based on high-order geodesic Voronoi partition is practically investigated. It allows multiple agents to monitor an area with obstacles to achieve the monitoring of the overall environment. As a result, the geodesic distance is introduced as a metric form. Based on the geodesic distance, point-by-point scanning on the layer is taken to achieve high-order Voronoi diagram division. The coverage algorithm can be implemented in a distributed manner through the exchange of location information with each other, and the Lloyd algorithm is added to realize the movement of the sensor toward the optimal position.
暂无评论