Xiaofeng Bai

Xiaofeng Bai

Auto-generated profile, based on publicly available information

Xiaofeng Bai

School of Instrumentation Science and Engineering, Harbin Institute of Technology, Harbin, China

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
16 September 2024 in IEEE Sensors Journal
Verified
Journal Article
Closed access
JMJianpeng Ma
Jianpeng Ma
XBXiaofeng Bai
Xiaofeng Bai
FMFang Ma
Fang Ma
GYGuangbin YU
Guangbin YU
BSBojun Sun
Bojun Sun
CLChengwei Li
Chengwei Li
Convolutional neural networks (CNNs) have been widely used in bearing fault diagnosis and have achieved promising results. However, due to interference from cage rotation frequency, diagnostic outcomes based on weak magnetic signals and traditional CNNs are often affected. To address this issue, this paper proposes a method based on Uniform Phase Intrinsic Time-Scale Decomposition (UPITD). By analyzing the correlation between weak magnetic signals and cage rotation frequency in the time domain, the method effectively separates fault signals from cage rotational signals. In addition, the input size and convolution kernel size in traditional CNNs are typically designed based on empirical values, which may not be optimal. Therefore, this paper determines the CNN input size based on the physical characteristics of weak magnetic signals, and optimizes the convolution kernel size using the decay rate of exponential function envelopes, further improving diagnostic accuracy. Experimental results show that the proposed method, based on UPITD and CNN, achieves a fault detection accuracy of greater than or equal to 99.34% across various bearing fault types, with a standard deviation of 0.002, which is significantly superior to traditional vibration-based methods. These results demonstrate the superiority and reliability of the proposed approach in bearing fault diagnosis.

24 February 2025 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
XBXiaofeng Bai
Xiaofeng Bai
AKAftab Alam Khan
Aftab Alam Khan
CLChengwei Li
Chengwei Li
JMJianpeng Ma
Jianpeng Ma
CLChengwei Li
Chengwei Li
Qazi Mazhar ul HaqQazi Mazhar ul Haq
Qazi Mazhar ul Haq
Cage slip in bearings is a key factor contributing to bearing failure and is also a crucial parameter for evaluating bearing health. However, existing methods for detecting cage slip are still inadequate. The cage slip is typically calculated by measuring the difference in rotational frequency between the cage and the inner ring. This paper presents an innovative monitoring method that achieves synchronous monitoring of the cage and inner ring frequencies by analyzing the variations in weak magnetic signals caused by remanent magnetism and the geomagnetic field, along with an adaptive ridge extraction algorithm. No additional modifications to the bearings are required. Furthermore, the method is not affected by environmental factors such as oil mist and high temperatures. Furthermore, the proposed adaptive ridge extraction algorithm dynamically balances the peak values and curve smoothness in the time-frequency graph of weak magnetic signals during rotational frequency extraction. It also dynamically adjusts the search bandwidth of the ridge and defines extraction regions to effectively avoid interference between the harmonic frequencies of the rolling elements and the rotational frequency of the inner ring, ensuring reliability of frequency extraction, especially during changes in spindle rotational frequency. This method can also locate bearing faults by analysing the fault characteristic frequencies in weak magnetic signals. The experimental results have validated the effectiveness of this method, demonstrating its significant contribution to the advancement of aircraft bearing condition monitoring technology.

25 April 2025 in IEEE Access
Verified
Journal Article
Open access
XBXiaofeng Bai
Xiaofeng Bai
Qazi Mazhar ul HaqQazi Mazhar ul Haq
Qazi Mazhar ul Haq
AKAftab Alam Khan
Aftab Alam Khan
CLChaohui Li
Chaohui Li
HAHind Alsharif
Hind Alsharif
CLChengwei Li
Chengwei Li
Ball bearings are prone to faults in their inner rings, outer rings, and rolling elements. Timely detection of these faults is crucial, especially when adversarial perturbations are present, as deep-learning-based fault diagnosis models may misclassify these faults. To address this issue, this paper proposes a hybrid adversarial learning method that combines convolutional neural networks with a generative adversarial network framework. In this method, the generator introduces perturbations and adaptively adjusts them based on their magnitudes and gradient information. The discriminator was used to verify the effectiveness of the adversarial perturbations. The goal of this hybrid adversarial learning method is to improve the fault recognition accuracy of a model when facing perturbation attacks. The experimental results show that under adversarial perturbation attacks, the proposed method outperforms other deep learning models and defense methods, demonstrating the effectiveness of this approach.

6 May 2026 in IEEE Sensors Journal
Verified
Journal Article
Closed access
AKAftab Alam Khan
Aftab Alam Khan
XBXiaofeng Bai
Xiaofeng Bai
Shafqat UllahShafqat Ullah
Shafqat Ullah
HDHao Duo
Hao Duo
CLChengwei Li
Chengwei Li
Unexploded ordnance (UXO) poses a persistent threat to safety in post-conflict areas, where manual clearance is slow, dangerous, and financially expensive. UAV-based real-time detection provides a more secure and scalable approach. However, UXO typically appear as small, low-contrast targets embedded in complex backgrounds, which significantly degrade the performance of conventional YOLO-based detectors. To address these challenges, this paper proposes UXO-YOLO, a lightweight, attention-enhanced YOLOv8s framework specifically designed for UXO detection in UAV imagery. A Spatial-Efficient Channel Attention (SECA) module is introduced in the neck to enhance fine-grained feature extraction and improve UXO-to-background discrimination while maintaining real-time efficiency. In addition, a C2f Coordinate Attention (C2f CA) module is integrated into the backbone to enable direction-aware feature encoding and improve localization robustness for small UXO targets. Furthermore, the large-scale P5 detection head is removed to eliminate unnecessary computation and focus the network on small-scale target detection. Owing to the sensitive and specific nature of UXO in military contexts, publicly available UXO-specific datasets are extremely limited. To address this limitation, a custom Unexploded Aerial Bomb (UAB) dataset was constructed using UAV-captured RGB images under controlled testing conditions. The proposed model is evaluated on the UAB dataset and further assessed on the public UAVDT benchmark to examine cross-domain robustness. Experimental results show that UXO-YOLO achieves 95.8% mAP50, 68.2% mAP50:95, and 91.9% recall on the UAB dataset, and 86.7% mAP50, 47.9% mAP50:95, and 81.8% recall on the UAVDT dataset, while preserving real-time inference efficiency. These results indicate the suitability of UXO-YOLO for UAV-based humanitarian UXO detection applications. The reported real-time performance is evaluated on a GPU-equipped laptop platform, and on-board validation on embedded UAV hardware remains part of future work.

24 October 2021
Verified
Conference Paper
Closed access
XBXiaofeng Bai
Xiaofeng Bai
ZLZijie Liao
Zijie Liao
Qian WangQian Wang
Qian Wang
JYJianning Yin
Jianning Yin
XLXingwen Li
Xingwen Li
Movable contact fallback may have disadvantageous effect on the interruption performance of low voltage molded case circuit breaker (MCCB). Based on short circuit experiments of one MCCB product, the occurrence of movable contact fallback phenomenon was predicted. In order to analyze the phenomenon more detailed, a multi-physical coupled model was proposed to simulate the interruption process. The model included three parts: firstly, the dynamic model of the operation mechanism was developed by ADAMS software, and its validity was verified by measuring the angular displacement of the main axis; secondly, the electro-magnetic forces acting on the movable contact and the armature of the magnetic release were calculated based on finite element method; finally, by embedding some self-programmed codes into ADAMS software to consider the above-mentioned electro-magnetic forces, the whole interruption process could be simulated. It demonstrates that the proposed model could be used to evaluate the interruption performance of MCCB qualitatively, especially for the movable contact fallback phenomenon.