Chaochao Guo
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Chaochao Guo has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Youchao Sun
College of Civil Aviation, Nanjing University of Aeronautics and Astronautics, Nanjing, China
6 shared publications - Chong Peng
Nanjing Univ Aeronaut & Astronaut, Coll Civil Aviat, 29 Jiangjun Ave, Nanjing 210016, Peoples R China
1 shared publication - Huibing Zhao
School of Traffic Engineering, Huang He Jiao Tong University, Jiaozuo, Henan, China
1 shared publication - Longbiao Li
Nanjing University of Aeronautics and Astronautics
1 shared publication Min Zhi
College of Civil Aviation, Nanjing University of Aeronautics and Astronautics, Nanjing, People’s Republic of China
1 shared publication- Rourou Yu
College of Civil Aviation, Nanjing University of Aeronautics and Astronautics, Nanjing, China
1 shared publication
Latest Publications
- 2 July 2026
- Published by Emerald Publishing in Engineering Computations
- Vol. 43 (10) , 4779-4802
Bayesian temporal factorization and improved transformer architecture for the prediction of aero-engine remaining useful life
Purpose: The purpose of this paper is to propose a comprehensive model that skillfully interpolates missing values without introducing potential bias, and performs high-precision prediction of the remaining useful life (RUL) of an engine using an improved transformer model. Design/methodology/approach: This paper proposes a method that integrates Bayesian temporal factorization with improved transformer architecture. By integrating low-rank matrix factorization and vector autoregressive (VAR) processes into a unified probabilistic graphical model, which enables the framework to capture both global and local consistency within large-scale time series data, is essential for robust RUL prediction. Additionally, a tailored Gibbs sampling algorithm is developed to impute missing spatiotemporal engine data effectively. Following the estimation of missing values, an improved transformer model is employed for RUL prediction, which leverages gated convolutional units to enhance its ability to fuse local contextual information at each time step, and harnesses bespoke gated attention units further to improve the computational efficiency of transformer models. Findings: Extensive experimentation on a turbofan engine dataset validates the efficacy of the proposed method. Results demonstrate that our approach either outperforms or is comparable to the best existing approaches in RUL estimation. Originality/value: The method proposed in this study addresses the problem of poor RUL prediction capability of traditional deep learning (DL) models when engine data are partially missing.
- 2 July 2026
- Published by Emerald Publishing in Engineering Computations
- Vol. 43 (10) , 4779-4802
Bayesian temporal factorization and improved transformer architecture for the prediction of aero-engine remaining useful life
Purpose: The purpose of this paper is to propose a comprehensive model that skillfully interpolates missing values without introducing potential bias, and performs high-precision prediction of the remaining useful life (RUL) of an engine using an improved transformer model. Design/methodology/approach: This paper proposes a method that integrates Bayesian temporal factorization with improved transformer architecture. By integrating low-rank matrix factorization and vector autoregressive (VAR) processes into a unified probabilistic graphical model, which enables the framework to capture both global and local consistency within large-scale time series data, is essential for robust RUL prediction. Additionally, a tailored Gibbs sampling algorithm is developed to impute missing spatiotemporal engine data effectively. Following the estimation of missing values, an improved transformer model is employed for RUL prediction, which leverages gated convolutional units to enhance its ability to fuse local contextual information at each time step, and harnesses bespoke gated attention units further to improve the computational efficiency of transformer models. Findings: Extensive experimentation on a turbofan engine dataset validates the efficacy of the proposed method. Results demonstrate that our approach either outperforms or is comparable to the best existing approaches in RUL estimation. Originality/value: The method proposed in this study addresses the problem of poor RUL prediction capability of traditional deep learning (DL) models when engine data are partially missing.
- 12 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 26 (4) , 5945-5957
DGNSCA: A Domain Generalized Network Leveraging Similarity and Class-Conditional Contrast for Robust Fault Diagnosis of Rotating Machinery Under Unseen Operating Conditions
Timely and accurate detection of bearing faults is critical to the reliability of rotating machinery, yet models trained under fixed conditions often fail in unseen domains owing to distribution shifts. To overcome this limitation, we develop DGNSCA—a domain generalization network that leverages similarity guidance, class-conditional feature alignment, and adversarial training to learn domain-agnostic, yet class-discriminative features. The architecture is built on a 1-D convolutional neural network and incorporates three key modules: global distribution alignment to extract domain-invariant features, class-conditional contrastive learning to enhance intraclass consistency across domains, and adversarial training to improve generalization. DGNSCA further introduces a domain-similarity-guided decision module that adaptively aggregates per-source predictions via similarity weights, enabling robust inference without access to target-domain data. Comprehensive evaluations on two widely recognized benchmark datasets show that DGNSCA consistently surpasses current leading methods regarding accuracy, precision, and F1-score. Ablation analyses further validate the distinct contribution of each module within the framework. These results indicate that DGNSCA provides a reliable and scalable solution for intelligent fault diagnosis under realistic, distribution-shifted operating conditions.
- 12 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 26 (4) , 5945-5957
DGNSCA: A Domain Generalized Network Leveraging Similarity and Class-Conditional Contrast for Robust Fault Diagnosis of Rotating Machinery Under Unseen Operating Conditions
Timely and accurate detection of bearing faults is critical to the reliability of rotating machinery, yet models trained under fixed conditions often fail in unseen domains owing to distribution shifts. To overcome this limitation, we develop DGNSCA—a domain generalization network that leverages similarity guidance, class-conditional feature alignment, and adversarial training to learn domain-agnostic, yet class-discriminative features. The architecture is built on a 1-D convolutional neural network and incorporates three key modules: global distribution alignment to extract domain-invariant features, class-conditional contrastive learning to enhance intraclass consistency across domains, and adversarial training to improve generalization. DGNSCA further introduces a domain-similarity-guided decision module that adaptively aggregates per-source predictions via similarity weights, enabling robust inference without access to target-domain data. Comprehensive evaluations on two widely recognized benchmark datasets show that DGNSCA consistently surpasses current leading methods regarding accuracy, precision, and F1-score. Ablation analyses further validate the distinct contribution of each module within the framework. These results indicate that DGNSCA provides a reliable and scalable solution for intelligent fault diagnosis under realistic, distribution-shifted operating conditions.
- 15 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Aerospace and Electronic Systems
- Vol. 62 (00189251) , 3093-3106
A Robust Continual Domain-Adaptation Framework for Gas-Path Fault Diagnosis of Aeroengine Under Dynamic Operating Conditions
Achieving reliable fault diagnosis of aero-engine gas path systems under dynamic operating conditions remains a critical challenge due to domain shifts across varying working states. To address this issue, we propose a Robust Continual Domain Adaptation Framework (RCDAF) that enables stable knowledge retention and adaptive transfer across a sequence of target domains. The framework initially leverages joint cross entropy and supervised contrastive loss to enhance intra-class compactness and inter-class separability. A memory buffer is then built to preserve logits, labels, and raw inputs from the source domain, facilitating the replay of knowledge. To mitigate feature distribution shifts during continual adaptation, we introduce a Controllable Batch Normalization (CBN) mechanism. Furthermore, a restraining past loss and dual-knowledge distillation loss are proposed to constrain representation drift while maintaining output consistency and discriminative capability. To address feature uncertainty, conditional entropy minimization is applied, and a pseudo-supervised contrastive (PSC) loss is designed to enable robust class-wise alignment, especially under label imbalance and pseudo-label noise. Lastly, a dynamic buffer update strategy ensures the continual evolution of stored knowledge. Comprehensive experiments on multi-domain aero-engine datasets validate the robustness and adaptability of RCDAF in complex, non-stationary diagnostic scenarios.
- 15 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Aerospace and Electronic Systems
- Vol. 62 (00189251) , 3093-3106
A Robust Continual Domain-Adaptation Framework for Gas-Path Fault Diagnosis of Aeroengine Under Dynamic Operating Conditions
Achieving reliable fault diagnosis of aero-engine gas path systems under dynamic operating conditions remains a critical challenge due to domain shifts across varying working states. To address this issue, we propose a Robust Continual Domain Adaptation Framework (RCDAF) that enables stable knowledge retention and adaptive transfer across a sequence of target domains. The framework initially leverages joint cross entropy and supervised contrastive loss to enhance intra-class compactness and inter-class separability. A memory buffer is then built to preserve logits, labels, and raw inputs from the source domain, facilitating the replay of knowledge. To mitigate feature distribution shifts during continual adaptation, we introduce a Controllable Batch Normalization (CBN) mechanism. Furthermore, a restraining past loss and dual-knowledge distillation loss are proposed to constrain representation drift while maintaining output consistency and discriminative capability. To address feature uncertainty, conditional entropy minimization is applied, and a pseudo-supervised contrastive (PSC) loss is designed to enable robust class-wise alignment, especially under label imbalance and pseudo-label noise. Lastly, a dynamic buffer update strategy ensures the continual evolution of stored knowledge. Comprehensive experiments on multi-domain aero-engine datasets validate the robustness and adaptability of RCDAF in complex, non-stationary diagnostic scenarios.
- 20 March 2025
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 36 (4) , 045006
The improved multi-scale convolution method for fault diagnosis of civil aircraft hydraulic systems based on QAR data
As a core system of the aircraft, the stability, response speed, and efficiency of the hydraulic system are directly linked to flight safety, control performance, and operational reliability. Hydraulic system failures can lead to catastrophic accidents. This paper proposes a diagnostic method for civil aircraft hydraulic systems based on quick access recorder (QAR) data. First, based on guidance from an airline’s maintenance records, eight typical hydraulic system faults were identified. Next, under the guidance of the hydraulic system’s working principles, 28 sensor parameters most relevant to hydraulic system faults were selected from over 3000 parameters collected by the aircraft’s sensors. Subsequently, using preprocessed QAR fault data, an improved deep learning model based on multi-scale convolution (MSC) was developed to diagnose hydraulic system faults. The model incorporates an enhanced MSC design, which employs cross-channel convolution on top of MSC and integrates a multi-head attention mechanism, enabling the model to extract multi-dimensional features from QAR data more quickly and accurately. Experimental results on the QAR fault dataset demonstrate high prediction accuracy and fast diagnostic speed, achieving an accuracy of 98.2%. This model effectively and accurately diagnoses hydraulic system faults, contributing to flight safety and improving maintenance efficiency.
- 20 March 2025
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 36 (4) , 045006
The improved multi-scale convolution method for fault diagnosis of civil aircraft hydraulic systems based on QAR data
As a core system of the aircraft, the stability, response speed, and efficiency of the hydraulic system are directly linked to flight safety, control performance, and operational reliability. Hydraulic system failures can lead to catastrophic accidents. This paper proposes a diagnostic method for civil aircraft hydraulic systems based on quick access recorder (QAR) data. First, based on guidance from an airline’s maintenance records, eight typical hydraulic system faults were identified. Next, under the guidance of the hydraulic system’s working principles, 28 sensor parameters most relevant to hydraulic system faults were selected from over 3000 parameters collected by the aircraft’s sensors. Subsequently, using preprocessed QAR fault data, an improved deep learning model based on multi-scale convolution (MSC) was developed to diagnose hydraulic system faults. The model incorporates an enhanced MSC design, which employs cross-channel convolution on top of MSC and integrates a multi-head attention mechanism, enabling the model to extract multi-dimensional features from QAR data more quickly and accurately. Experimental results on the QAR fault dataset demonstrate high prediction accuracy and fast diagnostic speed, achieving an accuracy of 98.2%. This model effectively and accurately diagnoses hydraulic system faults, contributing to flight safety and improving maintenance efficiency.
- 25 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-16
Deep Causal Disentanglement Network With Domain Generalization for Cross-Machine Bearing Fault Diagnosis
Domain generalization-based fault diagnosis (DGFD) has gained considerable attention in bearing fault diagnosis due to its ability to extract feature-invariant information from diverse source domains, without requiring direct access to target domain data. However, many existing DGFD approaches primarily rely on statistical models to capture the relationship between time-series data and labels. This often leads to the learning of entangled features, as these models lack prior knowledge to differentiate between task-relevant and task-irrelevant information. To address this limitation, this paper introduces the Deep Causal Disentanglement Network (DCDN), a novel approach tailored for cross-machine bearing fault diagnosis. In this framework, fault data collected from multiple source domains is decomposed into causal factors related to fault representation and non-causal factors associated with domain-specific information, using a structural causal model. This process effectively reconstructs the data generation pathway. By optimizing causal aggregation loss and maximizing information entropy loss, DCDN can distinguish between causal and non-causal features from both direct and indirect perspectives. Furthermore, a contrastive estimation loss is minimized to ensure that the extracted causal features retain most of the essential information from the original dataset. Additionally, a redundancy reduction loss is employed to minimize correlations among the dimensions of the causal vector, further reducing the entanglement between causal and non-causal factors. The effectiveness and superiority of the proposed model are demonstrated across five cross-machine bearing fault datasets. Experimental results show that, compared to other state-of-the-art (SOAT) methods, DCDN achieves superior performance in both estimation accuracy and robustness.
- 25 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-16
Deep Causal Disentanglement Network With Domain Generalization for Cross-Machine Bearing Fault Diagnosis
Domain generalization-based fault diagnosis (DGFD) has gained considerable attention in bearing fault diagnosis due to its ability to extract feature-invariant information from diverse source domains, without requiring direct access to target domain data. However, many existing DGFD approaches primarily rely on statistical models to capture the relationship between time-series data and labels. This often leads to the learning of entangled features, as these models lack prior knowledge to differentiate between task-relevant and task-irrelevant information. To address this limitation, this paper introduces the Deep Causal Disentanglement Network (DCDN), a novel approach tailored for cross-machine bearing fault diagnosis. In this framework, fault data collected from multiple source domains is decomposed into causal factors related to fault representation and non-causal factors associated with domain-specific information, using a structural causal model. This process effectively reconstructs the data generation pathway. By optimizing causal aggregation loss and maximizing information entropy loss, DCDN can distinguish between causal and non-causal features from both direct and indirect perspectives. Furthermore, a contrastive estimation loss is minimized to ensure that the extracted causal features retain most of the essential information from the original dataset. Additionally, a redundancy reduction loss is employed to minimize correlations among the dimensions of the causal vector, further reducing the entanglement between causal and non-causal factors. The effectiveness and superiority of the proposed model are demonstrated across five cross-machine bearing fault datasets. Experimental results show that, compared to other state-of-the-art (SOAT) methods, DCDN achieves superior performance in both estimation accuracy and robustness.
- Open Access
- 15 November 2024
- Published by Association for Computing Machinery (ACM)
- p. 25-31
Numerical Simulation Study of Cabin Fires in Civil Aircraft Based on Pyrosim
- 15 November 2024
- Published by Association for Computing Machinery (ACM)
- p. 25-31
Open AccessNumerical Simulation Study of Cabin Fires in Civil Aircraft Based on Pyrosim
- 25 September 2024
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 35 (12) , 126213
An improved similarity-based RUL prediction method considering degradation degree of multiple condition monitoring parameters for aero-engines
The aero-engine is the heart of an airplane. Predicting the remaining useful lifetime (RUL) of an aero-engine bears great significance, not only for improving the reliability and safety of the aero-engine but also for ensuring aircraft safety and performance. However, both issues, namely the selection of uncorrelated parameters for RUL estimation and the lack of a standard theoretical methodology for Health Index (HI) construction, inevitably impact the prediction accuracy. Here, we proposed an improved similarity-based RUL prediction method considering the degradation degree of multiple condition monitoring parameters for aero-engines. This method includes the improved minimum-redundancy maximum-relevancy approach for the quantitative selection of key parameters, and the similarity matching approach which takes into account the degradation degree of multiple parameters instead of constructing HI. The effectiveness of the proposed method was evaluated on turbine engine datasets. Experimental results show that (1) compared with other feature selection methods, the root mean square error (RMSE) of the proposed method is reduced by 12.3%; (2) compared with other RUL prediction methods, the RMSE of the proposed method is smaller than most methods but without a complicated training process. The results demonstrate that the proposed method achieves highly competitive prediction performance. By employing the proposed method, it is possible to significantly reduce the risk of engine failures, thereby improving safety and economic efficiency.
- 25 September 2024
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 35 (12) , 126213
An improved similarity-based RUL prediction method considering degradation degree of multiple condition monitoring parameters for aero-engines
The aero-engine is the heart of an airplane. Predicting the remaining useful lifetime (RUL) of an aero-engine bears great significance, not only for improving the reliability and safety of the aero-engine but also for ensuring aircraft safety and performance. However, both issues, namely the selection of uncorrelated parameters for RUL estimation and the lack of a standard theoretical methodology for Health Index (HI) construction, inevitably impact the prediction accuracy. Here, we proposed an improved similarity-based RUL prediction method considering the degradation degree of multiple condition monitoring parameters for aero-engines. This method includes the improved minimum-redundancy maximum-relevancy approach for the quantitative selection of key parameters, and the similarity matching approach which takes into account the degradation degree of multiple parameters instead of constructing HI. The effectiveness of the proposed method was evaluated on turbine engine datasets. Experimental results show that (1) compared with other feature selection methods, the root mean square error (RMSE) of the proposed method is reduced by 12.3%; (2) compared with other RUL prediction methods, the RMSE of the proposed method is smaller than most methods but without a complicated training process. The results demonstrate that the proposed method achieves highly competitive prediction performance. By employing the proposed method, it is possible to significantly reduce the risk of engine failures, thereby improving safety and economic efficiency.