Iterative learning control can be applied to systems that repeat the same task over a finite duration with resetting to the starting point once each one is complete. The idea of iterative learning control is to make u...
详细信息
Traditional diagnostic models for laser gyroscopes, widely utilized as high-precision angular velocity sensors in aerospace applications, often suffer from limited reliability and accuracy due to the difficulty of fea...
详细信息
Taste sensation can be objectively measured using electroencephalography (EEG) or electromyography (EMG). How-ever, it is still challenging to effectively utilize the complementary information from EEG and EMG signals...
详细信息
Taste sensation can be objectively measured using electroencephalography (EEG) or electromyography (EMG). How-ever, it is still challenging to effectively utilize the complementary information from EEG and EMG signals in taste sensation recognition. This paper proposes a bimodal fusion network (Bi-FusionNet) for recognizing basic taste sensations (sour, sweet, bitter, salty, umami, and blank). Two convolutional backbones with similar structures are designed to separately extract the single-modal features of EEG and EMG. Then, EEG and EMG features are concatenated for bimodal interaction and complementarity. Finally, three loss functions are adopted: a center loss for aggregating intra-class samples, a mean squared error loss for sequence positions for minimizing the difference between signals during the stimulation, and a softmax loss for minimizing the entropy of prediction and true labels. The results on the taste sensation dataset show that bimodal fusion improves recognition performance, and Bi-FusionNet outperforms single-modal methods and other fusion methods. Bi-FusionNet paves the way for the application of multimodal fusion in taste sensation recognition.
The systems actuated by Pneumatic Artificial Muscles (PAMs) are characterized by high nonlinearity and time-varying of their coefficients. Therefore, nonlinear and robust controllers are required to cope with these ch...
详细信息
To address the issues of lacking datasets and low recognition accuracy for paint film defects, this paper proposes a denoising diffusion implicit model (DDIM) for data augmentation of paint film defects and innovative...
详细信息
ISBN:
(数字)9798350386905
ISBN:
(纸本)9798350386912
To address the issues of lacking datasets and low recognition accuracy for paint film defects, this paper proposes a denoising diffusion implicit model (DDIM) for data augmentation of paint film defects and innovatively suggests a classification method combining Selective Kernel Networks (SKNet) with SqueezeNet model. Initially, the DDIM is used for dataset expansion, followed by an evaluation of the similarity between generated and captured paint film defect images using multiscale structural similarity (MS-SSIM). The training and generation effects of DDIM are then compared with those of DCGAN. In the SqueezeNet model, a Selective Kernel module is added following the fire7 module to enhance the model’s attention mechanism. The results show that all types of paint film defect images generated by DDIM have MS-SSIM indices above 0.64, with most exceeding 0.7. The combined approach of Selective Kernel Networks(SKNet) and SqueezeNet outperforms other attention mechanisms, achieving an accuracy above 96.3%. The method demonstrates promising prospects for paint film defect detection, enhancing identification efficiency and accuracy while reducing detection costs, and is applicable to mobile or embedded devices.
This article considers a rough neurocomputing approach to the design of the classify layer of a Brooks architecture for a robot control system. In the case of the line-crawling robot (LCR) described in this article, r...
详细信息
In contrast to the existing literature on berth allocation problem (BAP) considering fuel consumption and emissions in the terminal-centralized decision environment, the coordinated BAP in a decentralized decision env...
详细信息
In contrast to the existing literature on berth allocation problem (BAP) considering fuel consumption and emissions in the terminal-centralized decision environment, the coordinated BAP in a decentralized decision environment is proposed. The port and shipping lines are regarded as rational and autonomous agents, which is more reasonable and practical. Moreover, the study of discrete BAP is extended to the case of two adjacent ports in the same region. In the solution based on combinatorial auction, the port agent solves the BAP, and the vessel agent optimizes its sailing speed and arrival time. An extensive numerical experiment conducted and the results show that the proposed strategy can significantly reduce the total waiting time, the fuel consumption and mitigate the vessel emissions without severely compromising the service level of the ports, which can provide theoretical support for energy saving and emission reduction of ports from the operational perspective.
Knowledge quality and usability is core to a fault diagnosis system. Frame knowledge technique has been used to represent knowledge in many information and expert systems. To simplify the complexity of knowledge repre...
详细信息
Knowledge quality and usability is core to a fault diagnosis system. Frame knowledge technique has been used to represent knowledge in many information and expert systems. To simplify the complexity of knowledge representation in fault diagnosis expert system, a novel object-frame knowledge representation approach based on hierarchical model was proposed. In this approach, domain specific knowledge is expressed by combinations of object-frames. An Object-frame is composed by relevant state-object, test-object and rule-object or repair-object. Production rules are used to connect relevant objects' states. General features of object-frame and inference algorithm are introduced. Object-frame based knowledge items are stored in SQL database, inference engine performs the inference operation of knowledge using forward chaining strategy, implements reasoning, finds the cause of faults and gives repair suggestion driven by test data. Inference interpretation completes the task of explanation, which improved the clarity of reasoning. The advantage of this method is that we do not need knowledge representation language support. Experimental results show that the method proposed is effective, which improved the fault diagnosis and maintenance for a meteorological vehicle system.
In this paper, a kind of high speed and parallel hardware architecture is designed with one TMS320C6678 and one XC6VSX315T. This system is used for the pulsed Doppler radar. To map the algorithm effectively, pipeline ...
详细信息
ISBN:
(纸本)9781849196031
In this paper, a kind of high speed and parallel hardware architecture is designed with one TMS320C6678 and one XC6VSX315T. This system is used for the pulsed Doppler radar. To map the algorithm effectively, pipeline optimization on system and instruction levels are adopted, and various factors are taken into consideration, such as system complexity, communication between the processors, bandwidth of output signal.
The algebraic relationship between the transfer function and the state space representations of Linear Active Disturbance Rejection control (LADRC) is derived, upon which the unique frequency response characteristics ...
详细信息
The algebraic relationship between the transfer function and the state space representations of Linear Active Disturbance Rejection control (LADRC) is derived, upon which the unique frequency response characteristics of LADRC can be seen and understood. The transfer function form of LADRC for arbitrary order plant is derived from its state space representation and this allows that the open loop frequency characteristics of the LADRC based control system to be conveniently obtained and analyzed. The frequency response of LADRC not only shows excellent loop gain shape but also validates the original ADRC design concept: that the internal and external disturbances can be estimated in real time and cancelled. This time, the evidence comes not from simulation, or test, or time-domain analysis, but in the language of practicing engineers: frequency response.
暂无评论