In large-scale group decision-making (LSGDM) problems, clustering and feedback mechanisms play crucial roles in the consensus-building process. This study focuses on LSGDM problems that incorporate historical data in ...
详细信息
In large-scale group decision-making (LSGDM) problems, clustering and feedback mechanisms play crucial roles in the consensus-building process. This study focuses on LSGDM problems that incorporate historical data in dynamic social networks and introduces a novel consensus decision-making method. First, we define a picture fuzzy linguistic Euclidean distance metric, which effectively quantifies the distance between picture fuzzy linguistic information, providing a robust quantitative tool for related research. Second, we constructed a hybrid trust-based dynamic social network that enables decision-makers (DMs) to interact closely based on both trust relationships and preference similarities. This approach overcomes the limitations of existing studies that consider only trust relationships when constructing hybrid trust social networks. Additionally, we propose a novel clustering method that integrates hybrid trust networks and historical data. Furthermore, we address the identification and management of noncooperative behavior within the consensus feedback mechanism to enhance the efficiency of group consensus. Finally, a high-speed rail construction site selection problem is presented as a case study to demonstrate the effectiveness and superiority of the proposed method.
This paper investigates the problem of adaptive detection of radar targets in non-Gaussian clutter, where the target to be detected is considered to behave the dual-spread in the Doppler frequency dimension and the ra...
详细信息
This paper investigates the problem of adaptive detection of radar targets in non-Gaussian clutter, where the target to be detected is considered to behave the dual-spread in the Doppler frequency dimension and the range dimension. The clutter is assumed to follow the compound Gaussian model with lognormal texture and unknown covariance matrix structure. The multi-rank linear subspace model and the range-spread model are employed to depict the Doppler and range spread characteristics of target echoes. Then, the range-Doppler dual-spread adaptive radar target detector with lognormal-texture is proposed using the two-step generalized likelihood ratio criteria, which replaces the true values of the unknown parameters with their maximum likelihood and maximum a posteriori estimates. Experimental results on simulated and measured data demonstrate that the proposed detector shows superior performance in different clutter and target parameters compared to the competitors.
An intelligent welding robot system based on deep learning is designed. Firstly, the binocular vision system needs to be fixed and calibrated, and correct the left and right cameras to make the polar lines of the left...
详细信息
ISBN:
(纸本)9781728140940
An intelligent welding robot system based on deep learning is designed. Firstly, the binocular vision system needs to be fixed and calibrated, and correct the left and right cameras to make the polar lines of the left and right images collinear. Then, the left camera is used to take 1000 photos of arbitrary arranging fence. The position of the weld is marked by LabelImg software, and the training set and validation set are determined in a ratio of 3:1, and then used to train the convolutional neural network. After the loss function tends to converge, the training stops. The model optimizer converts the TensorFlow model into an IR model through the model optimizer in openvino, which is then deployed to the Raspberry Pi 3B+, which performs forward propagation through Intel's NCS2 edge computing stick to identify the location of the weld in the image. The exact position of the weld is found by machine vision, and the parallax of all the welds is calculated by matching with the right image, and the depth of the weld is obtained by calculation. Finally, transfer the UR3 robot through Ethernet and control it for automatic welding.
With increasing complexity and interconnectivity of the modern industrial systems, effectively diagnosing faults is a core step to Prognostic and Health Management (PHM). Language models, particularly Large Language M...
详细信息
With increasing complexity and interconnectivity of the modern industrial systems, effectively diagnosing faults is a core step to Prognostic and Health Management (PHM). Language models, particularly Large Language Models (LLMs) that pre-trained on massive corpora, have demonstrated remarkable capabilities in Natural Language Processing (NLP) and its related downstream tasks. However, how to leverage these models for facilitating system fault diagnosis and verify its effectiveness is rarely explored. This paper incorporates the potential comprehension ability of pre-trained LLMs, and investigates the efficacy of fine-tuning LLMs for realizing efficient system fault diagnosis. The experiments conducted in this study involve both open-source and closed-source models, and utilize a simulation and a real fault diagnosis dataset. We find that these models consistently achieve high performance across various metrics compared to the baselines. Additionally, qualitative and quantitative analysis is performed to investigate several aspects of the approach, such as the impact of dataset size, data normalization, missing values and explainability of the diagnosis, further showcasing the potential as well as limitations of the approach.
Unsafe behavior management is an effective way to prevent construction safety accidents. However, unsafe behavior management lacks personalization and needs to incorporate cognitive factors. Therefore, this study expl...
详细信息
Unsafe behavior management is an effective way to prevent construction safety accidents. However, unsafe behavior management lacks personalization and needs to incorporate cognitive factors. Therefore, this study explored the group cognitive characteristics of workers' unsafe behaviors under common individual factors. Firstly, the cognitive model of unsafe behavior was validated using structural equation modeling and bootstrap techniques. The results showed a distal mediating between the cognitive processes of unsafe behaviors. Second, the cognitive processes of workers' unsafe behaviors were analyzed using multiple group analysis for three individual factors: age, work experience, and education. The results showed that age is not a significant individual factor in group cognitive characteristics, education and work experience are significant individual factors with group cognitive characteristics of unsafe behavior. Workers with shorter experience are prone to cognitive failure in risk identification, others' influence, self-efficacy, and work skills. Workers with longer experience are prone to cognitive failure in safety awareness, others' pressure, and execution ability. Low-education workers are prone to cognitive failure in risk identification and pursuing energy-saving. High-education workers are prone to cognitive failure in safety awareness, self-efficacy, and work skills. Finally, targeted measures are given for significant individual factors based on group cognitive characteristics of unsafe behavior in order to construct widely used personalized group cognitive management for unsafe behavior.
Purpose Unsafe behavior is a major cause of safety accidents, while in most management measures for unsafe behavior, the construction workers are generally managed as a whole. Therefore, this study aims to propose gro...
详细信息
Purpose Unsafe behavior is a major cause of safety accidents, while in most management measures for unsafe behavior, the construction workers are generally managed as a whole. Therefore, this study aims to propose group management of construction workers' unsafe behavior considering individual characteristics. Design/methodology/approach A cognitive process model with ten cognitive factors was constructed based on cognitive safety theory. The questionnaire was developed and validated based on the cognitive model, and the results showed that the questionnaire had good reliability and validity, and the cognitive model fitted well. Latent class analysis was used to classify the unsafe behaviors of construction workers. Findings Four categories of cognitive excellent type, cognitive failure type, no fear type and knowingly offending type were obtained. Workers of cognitive excellent type have good cognitive ability and a small tendency for unsafe behaviors. Workers of cognitive failure type have poor cognitive ability and the potential for cognitive failure in all four cognitive links. Workers of no fear type have weak cognitive ability, and cognitive failure may occur in discovering information and choosing coping links. Workers of knowingly offending type have certain cognitive abilities, but cognitive failure may occur in choosing coping link. Originality/value This study formulates targeted management measures according to the potential characteristics of these four types and provides scientific theoretical support for the personalized management of unsafe behavior.
暂无评论