Ke Ma
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Ke Ma has a total of 19 co-authors. Here are the top co-authors by number of shared publications:
- Hongwei Wang
Zhejiang University, Hangzhou, China
3 shared publications Jian Zhang
College of Computer Science and Technology, Zhejiang University, Hangzhou, China
2 shared publications- Peng Peng
ZJU-UIUC Joint Institute, Zhejiang University, Haining, China
2 shared publications - Shuting Tao
College of Computer Science and Technology, Zhejiang University, Hangzhou, China
2 shared publications Bo Qin
Zhejiang University and the University of Illinois Urbana-Champaign Institute, Haining, China
1 shared publication- Bo Qin
Zhejiang University‐University of Illinois at Urbana‐Champaign Institute Zhejiang University Haining China
1 shared publication
Latest Publications
- 18 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 25 (1) , 1994-2007
Toward Unsupervised Domain Adaptation Fault Diagnosis: A Multisource Multitarget Method
Despite the remarkable results that can be achieved by data-driven intelligent methods developed for fault diagnosis, they typically presuppose the same distribution for the training and test data sets as well as sufficient labeled data. Various operating states often exist in practical scenarios, leading to a domain shift that hinders fault diagnosis effectiveness. While recent unsupervised domain adaptation methods have focused on cross-domain fault diagnosis, they can struggle to effectively utilize information from multiple source and target domains and achieve simultaneous fault diagnosis in multiple target domains. In this paper, we introduce an approach termed Weighted Joint Maximum Mean Discrepancy-enabled Multi-Source-Multi-Target Unsupervised Domain Adaptation (WJMMD-MDA) which facilitates domain adaptation in complex multi-source-multi-target settings, a previously unexplored area within this field. The proposed method can capture pertinent information from multiple source and target domains and induce domain alignment between these multiple domains via an improved weighted distance loss mechanism. Consequently, the model acquires domain-invariant and discriminative features across multiple source and target domains, thereby enabling the implementation of cross-domain fault diagnosis. The performance of the proposed method is evaluated in comprehensive comparative experiments on two datasets, and the experimental results demonstrate the superiority of this method when compared to the state-of-the-art methods.
- 18 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 25 (1) , 1994-2007
Toward Unsupervised Domain Adaptation Fault Diagnosis: A Multisource Multitarget Method
Despite the remarkable results that can be achieved by data-driven intelligent methods developed for fault diagnosis, they typically presuppose the same distribution for the training and test data sets as well as sufficient labeled data. Various operating states often exist in practical scenarios, leading to a domain shift that hinders fault diagnosis effectiveness. While recent unsupervised domain adaptation methods have focused on cross-domain fault diagnosis, they can struggle to effectively utilize information from multiple source and target domains and achieve simultaneous fault diagnosis in multiple target domains. In this paper, we introduce an approach termed Weighted Joint Maximum Mean Discrepancy-enabled Multi-Source-Multi-Target Unsupervised Domain Adaptation (WJMMD-MDA) which facilitates domain adaptation in complex multi-source-multi-target settings, a previously unexplored area within this field. The proposed method can capture pertinent information from multiple source and target domains and induce domain alignment between these multiple domains via an improved weighted distance loss mechanism. Consequently, the model acquires domain-invariant and discriminative features across multiple source and target domains, thereby enabling the implementation of cross-domain fault diagnosis. The performance of the proposed method is evaluated in comprehensive comparative experiments on two datasets, and the experimental results demonstrate the superiority of this method when compared to the state-of-the-art methods.
- 30 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 20 (8) , 9987-9996
Generalized Out-of-Distribution Fault Diagnosis (GOOFD) via Internal Contrastive Learning
Fault diagnosis is crucial in monitoring machines within industrial processes. With the increasing complexity of working conditions and demand for safety during production, diverse diagnosis methods are required, and an integrated fault diagnosis system capable of handling multiple tasks is highly desired. However, the diagnosis subtasks are often studied separately, and the current methods still need improvement for such a generalized system. To address this issue, we propose the generalized out-of-distribution fault diagnosis (GOOFD) framework to integrate diagnosis subtasks. Additionally, a unified fault diagnosis method based on internal contrastive learning and Mahalanobis distance is put forward to underpin the proposed generalized framework. The method involves feature extraction through internal contrastive learning and outlier recognition based on the Mahalanobis distance. Our proposed method can be applied to multiple fault diagnosis tasks and achieve better performance than the existing single-task methods. Experiments are conducted on benchmark and practical process datasets, indicating the effectiveness of the proposed framework.
- 30 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 20 (8) , 9987-9996
Generalized Out-of-Distribution Fault Diagnosis (GOOFD) via Internal Contrastive Learning
Fault diagnosis is crucial in monitoring machines within industrial processes. With the increasing complexity of working conditions and demand for safety during production, diverse diagnosis methods are required, and an integrated fault diagnosis system capable of handling multiple tasks is highly desired. However, the diagnosis subtasks are often studied separately, and the current methods still need improvement for such a generalized system. To address this issue, we propose the generalized out-of-distribution fault diagnosis (GOOFD) framework to integrate diagnosis subtasks. Additionally, a unified fault diagnosis method based on internal contrastive learning and Mahalanobis distance is put forward to underpin the proposed generalized framework. The method involves feature extraction through internal contrastive learning and outlier recognition based on the Mahalanobis distance. Our proposed method can be applied to multiple fault diagnosis tasks and achieve better performance than the existing single-task methods. Experiments are conducted on benchmark and practical process datasets, indicating the effectiveness of the proposed framework.
- Open Access
- 9 January 2023
- Published by Institution of Engineering and Technology (IET) in IET Collaborative Intelligent Manufacturing
- Vol. 5 (1)
A framework and prototype system in support of workflow collaboration and knowledge mining for manufacturing value chains
In the field of industrial design and manufacture, computer‐supported collaborative work (CSCW) systems have been widely deployed for better teamwork. However, the traditional CSCW systems have a main drawback in effectively processing and utilising knowledge across different industrial workflows. To bridge this gap, we propose a framework for collaboration between members across the manufacturing value chains to increase efficiency and reduce duplication in team cooperation. The framework contains three parts, namely workflow, knowledge mining, and services. Specifically, the workflow part provides a collaborative environment for multiple users. The knowledge mining part, as the core of the framework, extracts in‐context knowledge from workflows. The part of services can interact with users with different users in each workflow, including information recommendation they need in the future or information retrieval they want to know from other workflows. Furthermore, we develop a prototype system for supporting multiple value chains collaboration to verify the effectiveness and efficiency of the framework.
- 9 January 2023
- Published by Institution of Engineering and Technology (IET) in IET Collaborative Intelligent Manufacturing
- Vol. 5 (1)
Open AccessA framework and prototype system in support of workflow collaboration and knowledge mining for manufacturing value chains
In the field of industrial design and manufacture, computer‐supported collaborative work (CSCW) systems have been widely deployed for better teamwork. However, the traditional CSCW systems have a main drawback in effectively processing and utilising knowledge across different industrial workflows. To bridge this gap, we propose a framework for collaboration between members across the manufacturing value chains to increase efficiency and reduce duplication in team cooperation. The framework contains three parts, namely workflow, knowledge mining, and services. Specifically, the workflow part provides a collaborative environment for multiple users. The knowledge mining part, as the core of the framework, extracts in‐context knowledge from workflows. The part of services can interact with users with different users in each workflow, including information recommendation they need in the future or information retrieval they want to know from other workflows. Furthermore, we develop a prototype system for supporting multiple value chains collaboration to verify the effectiveness and efficiency of the framework.
- 15 February 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 71 (00189456) , 1-12
Progressively Balanced Supervised Contrastive Representation Learning for Long-Tailed Fault Diagnosis
In this article, a new fault diagnosis problem is formulated, which involves a large number of normal samples and in which almost all the fault classes are few-shot classes. Although this problem is common in many industrial scenarios, it remains a challenge overlooked in previous studies. To develop a novel solution for addressing this challenge, we employ long-tailed distribution in this work and name this new task the long-tailed fault diagnosis accordingly. Specifically, we divide the long-tailed fault diagnosis procedure into representation learning and classification. On this basis, we propose a method using progressively balanced supervised contrastive learning (PBS-SCL) for representation learning and a learnable linear classifier (LLC) for classification. The designed scheme consists of two phases. In the first phase, PBS-SCL is utilized to learn a more discriminative deep representation. In the second phase, an LLC is combined with the learned representation for better classification. Experiments are conducted on both the Tennessee Eastman process (TEP) benchmark dataset and a practical plasma etching process dataset. The results obtained show that the proposed method achieves significantly improved long-tailed fault diagnosis performance compared with existing methods.
- 15 February 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 71 (00189456) , 1-12
Progressively Balanced Supervised Contrastive Representation Learning for Long-Tailed Fault Diagnosis
In this article, a new fault diagnosis problem is formulated, which involves a large number of normal samples and in which almost all the fault classes are few-shot classes. Although this problem is common in many industrial scenarios, it remains a challenge overlooked in previous studies. To develop a novel solution for addressing this challenge, we employ long-tailed distribution in this work and name this new task the long-tailed fault diagnosis accordingly. Specifically, we divide the long-tailed fault diagnosis procedure into representation learning and classification. On this basis, we propose a method using progressively balanced supervised contrastive learning (PBS-SCL) for representation learning and a learnable linear classifier (LLC) for classification. The designed scheme consists of two phases. In the first phase, PBS-SCL is utilized to learn a more discriminative deep representation. In the second phase, an LLC is combined with the learned representation for better classification. Experiments are conducted on both the Tennessee Eastman process (TEP) benchmark dataset and a practical plasma etching process dataset. The results obtained show that the proposed method achieves significantly improved long-tailed fault diagnosis performance compared with existing methods.