Applied Soft Computing最新文献_第9页

The Fuzzified Grey Wolf: An improved grey wolf optimizer based on dynamic fuzzy system FGWO 模糊化灰狼：一种基于动态模糊系统FGWO的改进灰狼优化器

IF 6.6 1区计算机科学

Applied Soft Computing Pub Date : 2025-09-17 DOI: 10.1016/j.asoc.2025.113818

Mohammed Dheyaa Algubili , Labiba M. Alhelfi , Hana’ M. Ali

{"title":"The Fuzzified Grey Wolf: An improved grey wolf optimizer based on dynamic fuzzy system FGWO","authors":"Mohammed Dheyaa Algubili , Labiba M. Alhelfi , Hana’ M. Ali","doi":"10.1016/j.asoc.2025.113818","DOIUrl":"10.1016/j.asoc.2025.113818","url":null,"abstract":"<div><div>The Grey Wolf Optimizer (GWO) is a leading, powerful, and effective algorithm in swarm optimization techniques, showing competitive performance across various optimization problems. Yet, GWO is burdened by high tendencies toward exploitation and imprecise population diversity. This work introduces an improved GWO called the Fuzzified Grey Wolf Optimizer (FGWO) for solving global optimization problems. FGWO benefits from a dynamic fuzzy inference system (DFIS) to capture the optimal value of <span><math><mover><mrow><mi>a</mi></mrow><mo>→</mo></mover></math></span> throughout iterations. DFIS integrates two inputs: the diversity rate and iteration number, and by inferring the optimal value of <span><math><mover><mrow><mi>a</mi></mrow><mo>→</mo></mover></math></span>, FGOW determines whether to exploit or explore. Moreover, DFIS employs an adaptive membership function to capture the precise value of population diversity throughout the course of iteration. This optimal <span><math><mover><mrow><mi>a</mi></mrow><mo>→</mo></mover></math></span> determination strategy can achieve a balanced exploitation–exploration ratio, mitigating premature convergence and enhancing diversity. FGWO is evaluated on CEC2017 benchmark functions, four engineering designs, and a breast cancer genes feature selection design. FGWO was compared with three other improved GWOs, and across all experiments, the outcomes demonstrate its superiority in terms of efficiency and applicability to real-world designed problems.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"185 ","pages":"Article 113818"},"PeriodicalIF":6.6,"publicationDate":"2025-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145119839","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Heterogeneous feature selection with group structure mining in fuzzy decision systems for medical diagnosis 基于群结构挖掘的医学诊断模糊决策系统异构特征选择

IF 6.6 1区计算机科学

Applied Soft Computing Pub Date : 2025-09-17 DOI: 10.1016/j.asoc.2025.113913

Jihong Wan , Hongmei Chen , Li Xiao , Chuangpeng Shen , Wei Huang , Xiaoping Li

{"title":"Heterogeneous feature selection with group structure mining in fuzzy decision systems for medical diagnosis","authors":"Jihong Wan , Hongmei Chen , Li Xiao , Chuangpeng Shen , Wei Huang , Xiaoping Li","doi":"10.1016/j.asoc.2025.113913","DOIUrl":"10.1016/j.asoc.2025.113913","url":null,"abstract":"<div><div>In practical applications such as medical diagnosis and group decision making, the potential structural information contained in multi-dimensional features in the form of group domains plays an important role. However, most existing feature selection methods adopt transformed feature spaces for group structure analysis, which lack intrinsic semantic information interpretation. Meanwhile, fuzzy and uncertain heterogeneous data acquired from multiple devices increase the difficulty of task learning. Motivated by these two issues, this work devises a Heterogeneous Feature Selection method with Group Structure Mining in fuzzy decision systems (HFS-GSM), which follows the principle of one “strategy\" and one “mechanism\". Specifically, a feature group generation strategy based on fuzzy approximation Markov blanket is first designed for mining features with group structure, which introduces the concept of Markov blanket into the fuzzy rough set and utilizes the idea of approximation and fuzzy uncertainty measures. Then, a fuzzy dependency-based overlapping group elimination mechanism is proposed by attribution division, which avoids local redundancy while preserving global discriminative information. Furthermore, the effectiveness of HFS-GSM is verified in comparison with seven representative feature selection methods on publicly available medical datasets. Finally, medical diagnosis data provided by a hospital are obtained to demonstrate the reliability and utility of HFS-GSM in practical applications.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"185 ","pages":"Article 113913"},"PeriodicalIF":6.6,"publicationDate":"2025-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145159668","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Improving speech emotion recognition using gated cross-modal attention and multimodal homogeneous feature discrepancy learning 利用门控跨模态注意和多模态同质特征差异学习改进语音情感识别

IF 6.6 1区计算机科学

Applied Soft Computing Pub Date : 2025-09-17 DOI: 10.1016/j.asoc.2025.113915

Feng Li , Jiusong Luo , Wanjun Xia

{"title":"Improving speech emotion recognition using gated cross-modal attention and multimodal homogeneous feature discrepancy learning","authors":"Feng Li , Jiusong Luo , Wanjun Xia","doi":"10.1016/j.asoc.2025.113915","DOIUrl":"10.1016/j.asoc.2025.113915","url":null,"abstract":"<div><div>Speech emotion recognition (SER) remains a significant and crucial challenge due to the complex and multifaceted nature of human emotions. To tackle this challenge, researchers strive to integrate information from diverse modalities through multimodal learning. However, existing multimodal fusion techniques often overlook the intricacies of interactions between different modalities, resulting in suboptimal feature representations. In this paper, we propose WavFusion, a multimodal framework designed for SER that tackles key research challenges, such as effective multimodal fusion, modality heterogeneity, and discriminative representation learning. By utilizing a gated cross-modal attention mechanism and multimodal homogeneous feature discrepancy learning, WavFusion outperforms existing state-of-the-art methods on benchmark datasets. Our research highlights the importance of capturing subtle cross-modal interactions and learning discriminative representations for accurate multimodal SER. Experimental results indicate that the proposed method is highly competitive and better than most of the latest state-of-the-art methods for SER. WavFusion achieves 0.78 % and 1.27 % improvement in accuracy and 0.74 % and 0.44 % improvement in weighted F1 score over the previous methods on the IEMOCAP and MELD datasets, respectively.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"185 ","pages":"Article 113915"},"PeriodicalIF":6.6,"publicationDate":"2025-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145119679","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Multi-agent cooperation-based bi-criteria evolutionary many-objective optimization 基于多智能体合作的双准则进化多目标优化

IF 6.6 1区计算机科学

Applied Soft Computing Pub Date : 2025-09-17 DOI: 10.1016/j.asoc.2025.113865

Jiazheng Li , Yuan Liu , Juan Zou , Shuyi Liu , Shengxiang Yang , Jinhua Zheng

{"title":"Multi-agent cooperation-based bi-criteria evolutionary many-objective optimization","authors":"Jiazheng Li , Yuan Liu , Juan Zou , Shuyi Liu , Shengxiang Yang , Jinhua Zheng","doi":"10.1016/j.asoc.2025.113865","DOIUrl":"10.1016/j.asoc.2025.113865","url":null,"abstract":"<div><div>Many-objective evolutionary algorithms (MaOEAs) excel in solving many-objective optimization problems (MaOPs), which are mainly classified into two frameworks: the Pareto domination and the non-Pareto domination. The Pareto criterion (PC) obtains a well-converged solution set in multi-objective spaces through the Pareto dominance relationship between solutions. However, insufficient environmental selection pressure in many-objective spaces leads to slow convergence. The non-Pareto criterion (NPC) enhances the selection pressure by evaluating the solution set with a set of sortable scalar values. However, it is difficult to ensure the Pareto-optimal consistency of convergence and distribution when facing highly irregular Pareto fronts (PFs). Therefore, combining the two sets of criteria can satisfy the demand for uniform distribution while bringing significant selection pressure. A multi-agent cooperative strategy is proposed in this study to realize the combination of the two criteria. This strategy controls the evolutionary direction of two populations separately by deploying two agents, and promotes cooperative evolution between these populations through the exchange and flow of large amounts of information. In order to better realize the cooperative effect, we adopt the multi-agent reinforcement learning (MARL) strategy to accurately regulate the variation operator and parameter configurations of the bi-population. In addition, the effectiveness of the proposed method is validated on 74 test problems (DTLZ, WFG, and UF) and 3 real-world problems. The results show that the proposed algorithm is more competitive than 6 state-of-the-art algorithms.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"185 ","pages":"Article 113865"},"PeriodicalIF":6.6,"publicationDate":"2025-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145159719","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Fuzzy Lagrange interpolation method from summation of interactive fuzzy numbers 交互式模糊数求和的模糊拉格朗日插值方法

IF 6.6 1区计算机科学

Applied Soft Computing Pub Date : 2025-09-17 DOI: 10.1016/j.asoc.2025.113817

Geizane Lima da Silva , Estevão Esmi , Vinícius Francisco Wasques , Laécio Carvalho de Barros

{"title":"Fuzzy Lagrange interpolation method from summation of interactive fuzzy numbers","authors":"Geizane Lima da Silva , Estevão Esmi , Vinícius Francisco Wasques , Laécio Carvalho de Barros","doi":"10.1016/j.asoc.2025.113817","DOIUrl":"10.1016/j.asoc.2025.113817","url":null,"abstract":"<div><div>This article proposes a novel approach to extending the sum of interactive fuzzy numbers, which is independent of the order of its operands. Interactive fuzzy numbers are fuzzy quantities in which the values across different <span><math><mi>α</mi></math></span>-cuts are not assumed to vary independently, incorporating dependencies that better reflect real-world uncertainty. A characterization of the proposed summation is given in terms of <span><math><mi>α</mi></math></span>-cuts, making computational implementation easier. It is shown that this operation preserves essential mathematical properties, including associativity. This is particularly important, as it enables the consistent aggregation of multiple fuzzy quantities without concern for the order in which the operands are grouped. The norm and width behaviors under this new summation are also analyzed. To illustrate the theoretical results, several examples are provided. As a practical application, the classical Lagrange polynomial interpolation method is extended to handle uncertain parameters represented by interactive fuzzy numbers. A fuzzy curve fitting problem is examined using this framework, and a comparative discussion highlights the advantages of the proposed method over existing approaches.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"185 ","pages":"Article 113817"},"PeriodicalIF":6.6,"publicationDate":"2025-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145119833","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

DT and LLM driven intelligent maintenance system for L-DED and DAG-based LLM fault diagnosis evaluation framework 基于DT和LLM驱动的L-DED智能维护系统和基于dag的LLM故障诊断评估框架

IF 6.6 1区计算机科学

Applied Soft Computing Pub Date : 2025-09-17 DOI: 10.1016/j.asoc.2025.113942

Jian Tang , Shitong Peng , Jianan Guo , Danya Song , Dongna Gao , Weiwei Liu , Fengtao Wang

{"title":"DT and LLM driven intelligent maintenance system for L-DED and DAG-based LLM fault diagnosis evaluation framework","authors":"Jian Tang , Shitong Peng , Jianan Guo , Danya Song , Dongna Gao , Weiwei Liu , Fengtao Wang","doi":"10.1016/j.asoc.2025.113942","DOIUrl":"10.1016/j.asoc.2025.113942","url":null,"abstract":"<div><div>Metal additive manufacturing (AM) has revolutionized industries such as aerospace and automotive manufacturing due to its ability to rapidly prototype complex structures. Laser Directed Energy Deposition (L-DED) is a key AM technique, offering high deposition rates and superior mechanical properties. However, the inherent complexity and high cost of L-DED equipment demand reliable maintenance management to minimize downtime. Traditional maintenance approaches struggle to keep pace with escalating production demands and to cope with growing equipment complexity. To address this, we propose a dual-driven intelligent maintenance system for L-DED, integrating Digital Twins (DT) and Large Language Models (LLMs). The system features a comprehensive DT framework that synchronizes the virtual entity with the physical one in real time, it also incorporates an intelligent maintenance Q&A assistant powered by Retrieval-Augmented Generation (RAG), leveraging L-DED maintenance knowledge bases to provide accurate operational support. Additionally, we propose a Directed Acyclic Graphs (DAG)-based framework to assess LLMs’ ability to guide users through complete fault diagnosis. Our work aims to enhance the reliability and efficiency of L-DED maintenance through advanced digital technologies, ultimately improving productivity and reducing downtime in additive manufacturing.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"185 ","pages":"Article 113942"},"PeriodicalIF":6.6,"publicationDate":"2025-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145097973","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Pathology characteristics-aware federated learning for weakly supervised nuclei segmentation 弱监督核分割的病理特征感知联合学习

IF 6.6 1区计算机科学

Applied Soft Computing Pub Date : 2025-09-17 DOI: 10.1016/j.asoc.2025.113894

Yi Qian , Xipeng Pan , Yimin Wen , Xinjun Bian , Shilong Song

{"title":"Pathology characteristics-aware federated learning for weakly supervised nuclei segmentation","authors":"Yi Qian , Xipeng Pan , Yimin Wen , Xinjun Bian , Shilong Song","doi":"10.1016/j.asoc.2025.113894","DOIUrl":"10.1016/j.asoc.2025.113894","url":null,"abstract":"<div><div>In federated learning, a key challenge in nuclei segmentation lies in data heterogeneity, primarily resulting from the diverse sources of pathology images. Nuclei in pathological images are typically small and densely distributed, making accurate annotation highly labor-intensive and reliant on specialized expertise. Weakly supervised learning is widely adopted for this task, as it only requires point annotations at the centers of nuclei. However, point annotations lack precise boundary information, thereby exacerbating the difficulties introduced by data heterogeneity. To address this issue, we propose a preprocessing strategy that leverages the unique optical properties of H&E stained images to generate Contrast-Difference Enhanced Images (CDEI). These CDEI highlight nucleus boundaries to varying extents based on the tonal characteristics of H&E stained images. Building on this strategy, we propose a Multi-source Hierarchical Enhancement Network (MHEN) as the client-side architecture. MHEN takes both the H&E stained images and the corresponding CDEI as input, effectively mitigating the limitations of weak labels by incorporating enhanced boundary cues. Furthermore, considering the characteristics of nuclei segmentation, we design a Federated Nuclei-Weighted Aggregation strategy on the server side. This strategy estimates each client’s contribution to the global model by quantifying the number of nuclei present in its local pathology images. To thoroughly assess the effectiveness of our approach, we compare it with both conventional weakly supervised methods and existing federated weak supervision frameworks. The experimental results demonstrate that our proposed federated learning framework for weakly supervised nuclei segmentation significantly outperforms existing methods. Our source code is available on GitHub.<span><span><sup>1</sup></span></span></div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"185 ","pages":"Article 113894"},"PeriodicalIF":6.6,"publicationDate":"2025-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145222103","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Span-level emotion-cause-category triplet extraction with instruction tuning LLMs and data augmentation 基于指令调优llm和数据增强的跨层情感-原因-类别三元组提取

IF 6.6 1区计算机科学

Applied Soft Computing Pub Date : 2025-09-17 DOI: 10.1016/j.asoc.2025.113938

Xiangju Li , Dong Yang , Xiaogang Zhu , Faliang Huang , Peng Zhang , Zhongying Zhao

{"title":"Span-level emotion-cause-category triplet extraction with instruction tuning LLMs and data augmentation","authors":"Xiangju Li , Dong Yang , Xiaogang Zhu , Faliang Huang , Peng Zhang , Zhongying Zhao","doi":"10.1016/j.asoc.2025.113938","DOIUrl":"10.1016/j.asoc.2025.113938","url":null,"abstract":"<div><div>Span-level emotion-cause-category triplet extraction is a fine-grained task in emotion cause analysis that aims to identify emotion spans, cause spans, and their corresponding emotion categories from documents. Existing methods, including clause-level emotion-cause pair extraction and span-level emotion-cause detection, often suffer from redundant information and difficulties in accurately classifying emotion categories, particularly when emotions are expressed implicitly or ambiguously. To overcome these challenges, this study explores a fine-grained approach to span-level emotion-cause-category triplet extraction and introduces an innovative framework that leverages instruction tuning and data augmentation techniques based on large language models. The proposed method employs task-specific triplet extraction instructions and utilizes low-rank adaptation to fine-tune large language models, eliminating the necessity for intricate task-specific architectures. Furthermore, an LLM-based data augmentation strategy is developed to address data scarcity by guiding large language models in generating high-quality synthetic training data. Extensive experimental evaluations demonstrate that the proposed approach significantly outperforms existing baseline methods, achieving at least a 12.8 % improvement in span-level emotion-cause-category triplet extraction metrics. The results demonstrate the method’s effectiveness and robustness, offering a promising avenue for advancing research in emotion cause analysis.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"185 ","pages":"Article 113938"},"PeriodicalIF":6.6,"publicationDate":"2025-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145158923","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A fast and robust ensemble evolving pixel cloud-based image segmentation approach 一种快速鲁棒的集成进化像素云图像分割方法

IF 6.6 1区计算机科学

Applied Soft Computing Pub Date : 2025-09-16 DOI: 10.1016/j.asoc.2025.113926

Tao Zhang , Hai-Jun Rong , Zhao-Xu Yang , Chi-Man Vong

{"title":"A fast and robust ensemble evolving pixel cloud-based image segmentation approach","authors":"Tao Zhang , Hai-Jun Rong , Zhao-Xu Yang , Chi-Man Vong","doi":"10.1016/j.asoc.2025.113926","DOIUrl":"10.1016/j.asoc.2025.113926","url":null,"abstract":"<div><div>The existing cluster-based image segmentation algorithms have the burden of iterative computation caused by the change of cluster centers and are sensitive to noise. In this paper, we present a fast and robust ensemble evolving pixel cloud-based image segmentation approach. The concept of pixel clouds by clustering pixels of the same pattern around their focal pixels is proposed. The following attributes distinguish the proposed algorithm: (1) The pixel clouds are evolvable according to the global densities of the incoming pixels and the number of pixel clouds is automatically determined. (2) The focal pixels of pixel clouds are dynamically updated with the highest local densities by using the recursive density estimation, which avoids redundant distance calculations when a new pixel arrives. (3) A multiscale morphological gradient reconstruction operation is employed to merge or filter meaningless pixel clouds, especially in noisy images, which helps to adaptively polish neighboring pixel clouds and compact the pixel clouds. (4) An ensemble structure is introduced to fasten the image segmentation speed by splitting the whole image into multiple independent sub-images, in which the pixel clouds are independently formed and evolved. Comprehensive experiments on natural images, remote sensing images and medical images reveal that the proposed approach surpasses the state-of-the-art algorithms in both segmentation accuracy and computational efficiency. Even for the noisy images, the proposed approach demonstrates more robust performance.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"185 ","pages":"Article 113926"},"PeriodicalIF":6.6,"publicationDate":"2025-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145119838","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Large model for fault diagnosis of industrial equipment based on a knowledge graph construction 基于知识图谱构建的工业设备故障诊断大模型

IF 6.6 1区计算机科学

Applied Soft Computing Pub Date : 2025-09-16 DOI: 10.1016/j.asoc.2025.113936

Jichao Zhuang , Jiaming Yang , Weigang Li , Jian Chen , Yunjun Zheng , Zhuyun Chen

{"title":"Large model for fault diagnosis of industrial equipment based on a knowledge graph construction","authors":"Jichao Zhuang , Jiaming Yang , Weigang Li , Jian Chen , Yunjun Zheng , Zhuyun Chen","doi":"10.1016/j.asoc.2025.113936","DOIUrl":"10.1016/j.asoc.2025.113936","url":null,"abstract":"<div><div>To address the significant heterogeneity of multi-modal data and the challenges in capturing fault semantics for industrial equipment, a fault diagnosis framework that integrates a time-frequency knowledge graph with the large model DeepSeek-V3 is proposed. Specifically, an unsupervised knowledge graph construction method is designed based on multi-modal vibration data signals. This method mines temporal evolution relationships using dynamic time warping and quantifies the relevance between features and faults via mutual information, thereby forming a dynamic graph representation. Additionally, DeepSeek-V3 encodes the natural language descriptions of vibration features, integrating graph structure and time-frequency map features to achieve collaborative reasoning and diagnosis among text, graphs, and maps. Experimental results show that the proposed method achieves high accuracy and significantly outperforms benchmark models, surpassing traditional methods. The proposed framework, through the deep integration of data-driven knowledge graphs and large model semantic understanding, demonstrates high precision, strong robustness, and transparent decision-making capabilities, providing new insights for intelligent diagnosis of industrial equipment.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"185 ","pages":"Article 113936"},"PeriodicalIF":6.6,"publicationDate":"2025-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145119757","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0