JZJian Zhou

Jian Zhou

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Jian Zhou has a total of 16 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Digital Twin-Based Virtual Sensing for Real-Time Process Monitoring of Marine Reciprocating Natural Gas Compressor Packages

    by Xiang Li, Xiaoying Zhang, Jiatong Ling, Jian Zhou, Hang Zhang

    Marine reciprocating compressor packages are critical in offshore oil and gas production but face inherent challenges for process monitoring due to explosion-proof requirements and limited onboard sensing. Many key process variables, such as flow rates and stage-wise efficiencies, remain unmeasured in practice, hindering comprehensive and accurate real-time monitoring. This study proposes a digital twin-based virtual sensing approach that integrates process mechanism modeling with real-time data streams to infer unmeasured variables from limited measurements and reconstruct package-level operating states. A full package-level process mechanism model was established in HYSYS, incorporating compression, heat exchange, and recycle control modules, and further generalized through a cascaded-stage modeling strategy that supports scalable deployment across packages with different configurations. A DT framework was constructed to couple the model with real-time sensor inputs, enabling continuous model updating, virtual-physical synchronization, and visualization through a service platform. Validation on a two-stage marine compressor package shows that predicted data closely match operating and design values, with MAPE typically <2% for compressor metrics, heat exchanger water flow MAPE≈1.4–1.5%, and recycle flow MAPE≈9.6%. Additional testing on a small-scale compressor package confirms the scalability of the cascaded-stage modeling approach and the DT system, maintaining flow-prediction errors within 5% while requiring only minimal interface configuration and parameter adjustment for direct deployment across packages. These results indicate that the proposed method can effectively extend monitoring capability beyond limited sensor coverage, providing a practical pathway for DT-enabled monitoring and supervisory optimization of marine reciprocating compressor packages.


  • Open Access

    A Digital Twin System for Adaptive Aligning of Large Cylindrical Components

    by Wei Fan, Ruoyao Xiao, Jieru Zhang, Linayu Zheng, Jian Zhou

    Most large aerospace cylindrical components still adopt a manual aligning method with low automation, large manual intervention, and heavy dependence on operator workers, resulting in the low quality and efficiency of large component aligning, which seriously prolongs the manufacturing time of aerospace products. To cope with this issue, based on closed-loop adaptive control and digital twin (DT) technologies, an adaptive aligning system for large cylindrical components, i.e., the DT aligning system, is proposed in this study. For the DT aligning system, through the DT multi-dimensional modeling, i.e., geometric modeling, physical modeling, functional modeling, and data modeling, it can be divided into a physical space, a virtue space, and twin data. Note that the association, mapping, and interaction between physical space and virtual space of the aligning system can be realized via the twin data, thereby realizing real-time virtual display, monitoring, and control of the large component aligning. In addition, based on the measured pose data, aligning stress, and predicted aligning error, an adaptive force/position control method for large component aligning is proposed, and it can achieve real-time decision-making and precise execution of the aligning process. Finally, through application validation, the DT process system can realize the real-time status perception and process execution decision during the large component aligning. Finally, through experimental validation, it is found that the proposed system, i.e., the DT aligning system, can improve the quality and efficiency of the large aerospace cylindrical component aligning, as well as the automation and intelligent level of the aligning system.


  • Open Access

    Online Surface Roughness Prediction for Assembly Interfaces of Vertical Tail Integrating Tool Wear under Variable Cutting Parameters

    by Yahui Wang, Yiwei Wang, Lianyu Zheng, Jian Zhou

    Monitoring surface quality during machining has considerable practical significance for the performance of high-value products, particularly for their assembly interfaces. Surface roughness is the most important metric of surface quality. Currently, the research on online surface roughness prediction has several limitations. The effect of tool wear variation on surface roughness is seldom considered in machining. In addition, the deterioration trend of surface roughness and tool wear differs under variable cutting parameters. The prediction models trained under one set of cutting parameters fail when cutting parameters change. Accordingly, to timely monitor the surface quality of assembly interfaces of high-value products, this paper proposes a surface roughness prediction method that considers the tool wear variation under variable cutting parameters. In this method, a stacked autoencoder and long short-term memory network (SAE–LSTM) is designed as the fundamental surface roughness prediction model using tool wear conditions and sensor signals as inputs. The transfer learning strategy is applied to the SAE–LSTM such that the surface roughness online prediction under variable cutting parameters can be realized. Machining experiments for the assembly interface (using Ti6Al4V as material) of an aircraft’s vertical tail are conducted, and monitoring data are used to validate the proposed method. Ablation studies are implemented to evaluate the key modules of the proposed model. The experimental results show that the proposed method outperforms other models and is capable of tracking the true surface roughness with time. Specifically, the minimum values of the root mean square error and mean absolute percentage error of the prediction results after transfer learning are 0.027 μm and 1.56%, respectively.


  • Automated Model Generation for Machinery Fault Diagnosis Based on Reinforcement Learning and Neural Architecture Search

    by Jian Zhou, Lianyu Zheng, Yiwei Wang, Cheng Wang, Robert X. Gao

    In recent years, deep learning (DL)-based fault diagnosis methods have demonstrated significant success in various domains due to their high accuracy. Similar to other data-driven techniques, DL models are application-specific and strongly depend on the data which they are developed upon. Different DL models need to be designed for different tasks. In addition, manual-tuning of the DL structures and associated parameters as part of the model design is a trial-and-error optimization process, which is time-consuming and sensitive to changes. To address these limitations, this article presents a reinforcement learning (RL) and neural architecture search (NAS)-based automatic modeling framework (RL-NAS) for fault diagnosis of machinery. The RL-NAS method can adaptively and automatically design high-accuracy network models according to the intended diagnosis tasks. A weight-sharing mechanism has been developed to alleviate the bottleneck of NAS where the computation time increases exponentially with the expansion of the search space and the deepening of the model structure. To evaluate its effectiveness, efficiency, and reproducibility, the proposed framework is validated on five datasets from different institutes, spanning the applications of rolling element bearings, gears, and ball screws. The results show that for all five applications, the RL-NAS method successfully searched out diagnostics models with over 97% accuracy within a short time, from 40 s to 30 min depending on the complexity of the diagnosis task, showing good performance of the proposed method.