Jiakai Ding

Mr. Jiakai Ding

Hunan Provincial Key Laboratory of Health Maintenance for Mechanical Equipment, Hunan University of Science and Technology
orcid

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

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

Representative Publications

View All Publications
21 January 2020 in IEEE Access
Verified
Journal Article
Open access
JDJiakai Ding
Jiakai Ding
DXDongming Xiao
Dongming Xiao
XLXuejun Li
Xuejun Li
The decomposition number K and penalty factor α in the variational mode decomposition (VMD) algorithm have a great influence on the decomposition effect and the accuracy of subsequent fault diagnosis. Therefore, a gear fault diagnosis method based on genetic mutation particle swarm optimization VMD and probabilistic neural network (GMPSO-VMD-PNN) algorithm is proposed in this paper. Firstly, the GMPSO algorithm is used to optimize the [K,α] parameter combination in the VMD algorithm, and the optimal [K,α] parameter combination of each gear fault vibration signal to be decomposed is selected. Then, the gear fault vibration signal is decomposed into several intrinsic mode functions (IMFs) by VMD, and the sample entropy value of each IMFs is extracted to form the feature vector of subsequent fault diagnosis. Finally, the characteristic vector of gear fault vibration signal is input into PNN model, and gear fault is accurately classified. By comparing with fixed parameter VMD algorithm, empirical mode decomposition (EMD) and complete ensemble empirical mode decomposition adaptive noise (CEEMDAN) algorithm, the superiority of this method in gear fault diagnosis is verified. Therefore, the GMPSO-VMD-PNN algorithm proposed in this paper has certain application value for gear fault diagnosis.

31 March 2020 in Sensors
Verified
Journal Article
Open access
PDF file
JDJiakai Ding
Jiakai Ding
LHLiangpei Huang
Liangpei Huang
DXDongming Xiao
Dongming Xiao
XLXuejun Li
Xuejun Li
The vibration signal of an early rolling bearing is nonstationary and nonlinear, and the fault signal is weak and difficult to extract. To address this problem, this paper proposes a genetic mutation particle swarm optimization variational mode decomposition (GMPSO-VMD) algorithm and applies it to rolling bearing vibration signal fault feature extraction. Firstly, the minimum envelope entropy is used as the objective function of the GMPSO to find the optimal parameter combination of the VMD algorithm. Then, the optimized VMD algorithm is used to decompose the vibration signal of the rolling bearing and several intrinsic mode functions (IMFs) are obtained. The envelope spectrum analysis of GMPSO-VMD decomposed rolling bearing fault signal IMF1 was carried out. Moreover, the feature frequency of the four fault states of the rolling bearing are extracted accurately. Finally, the GMPSO-VMD algorithm is utilized to analyze the simulation signal and rolling bearing fault vibration signal. The effectiveness of the GMPSO-VMD algorithm is verified by comparing it with the fixed parameter VMD (FP-VMD) algorithm, complete ensemble empirical mode decomposition adaptive noise (CEEMDAN) algorithm and empirical mode decomposition (EMD) algorithm.

11 December 2019 in Applied Sciences
Verified
Journal Article
Open access
PDF file
DXDongming Xiao
Dongming Xiao
JDJiakai Ding
Jiakai Ding
XLXuejun Li
Xuejun Li
LHLiangpei Huang
Liangpei Huang
A gear fault diagnosis method based on kurtosis criterion variational mode decomposition (VMD) and self-organizing map (SOM) neural network is proposed. Firstly, the VMD algorithm is used to decompose the gear vibration signal, and the instantaneous frequency mean is calculated as the evaluation index, and the characteristic curve is drawn to screen out the most relevant intrinsic mode functions (IMFs) of the original vibration signal. Then, the number of VMD decompositions is determined, and the kurtosis value of IMFs are extracted to form the feature vectors. Then, the kurtosis value feature vectors of IMFs are normalized to form the kurtosis value normalized vectors. Finally, the normalized vectors of kurtosis value are input into SOM neural network to realize gear fault diagnosis. When the number of training times of SOM neural network is 100, the gear fault category is accurately classified by SOM neural network. The results show that when the training times of SOM neural network is 100 times, the gear fault diagnosis method, based on the kurtosis criterion VMD and SOM neural network is 100%, which indicates that the new method has a good effect on gear fault diagnosis.

18 December 2020 in Mathematical Problems in Engineering
Verified
Journal Article
Open access
JDJiakai Ding
Jiakai Ding
DXDongming Xiao
Dongming Xiao
LHLiangpei Huang
Liangpei Huang
XLXuejun Li
Xuejun Li
The gear fault signal has some defects such as nonstationary nonlinearity. In order to increase the operating life of the gear, the gear operation is monitored. A gear fault diagnosis method based on variational mode decomposition (VMD) sample entropy and discrete Hopfield neural network (DHNN) is proposed. Firstly, the optimal VMD decomposition number is selected by the instantaneous frequency mean value. Then, the sample entropy value of each intrinsic mode function (IMF) is extracted to form the gear feature vectors. The gear feature vectors are coded and used as the memory prototype and memory starting point of DHNN, respectively. Finally, the coding vector is input into DHNN to realize fault pattern recognition. The newly defined coding rules have a significant impact on the accuracy of gear fault diagnosis. Driven by self-associative memory, the coding of gear fault is accurately classified by DHNN. The superiority of the VMD-DHNN method in gear fault diagnosis is verified by comparing with an advanced signal processing algorithm. The results show that the accuracy based on VMD sample entropy and DHNN is 91.67% of the gear fault diagnosis method. The experimental results show that the VMD method is better than the complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) and empirical mode decomposition (EMD), and the effect of it in the diagnosis of gear fault diagnosis is emphasized.

29 July 2025 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
DXDongming Xiao
Dongming Xiao
JDJianhong Diao
Jianhong Diao
JDJiakai Ding
Jiakai Ding
LJLingli Jiang
Lingli Jiang
CZChunhua Zhao
Chunhua Zhao
Deep learning has demonstrated strong capabilities in rotating machinery fault diagnosis, yet it heavily depends on large amount of labeled data, which are often costly to obtain. Moreover, traditional federated learning struggles with model drift and communication inefficiency under non-IID data conditions. To tackle these challenges, we proposed a dynamic federated aggregation algorithm guided by the Rademacher complexity of client data named FedRad. Furthermore, a controllable non-IID data construction strategy based on hybrid distributions is presented to better reflect real-world industrial data characteristics. FedRad leverages lightweight models MDSE-Net to reduce computational overhead while improving generalization performance in heterogeneous settings. Experiments on two datasets confirm the method’s superior accuracy and robustness, making it a promising solution for distributed fault diagnosis in complex industrial scenarios.

13 May 2024 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
JDJiakai Ding
Jiakai Ding
YWYi Wang
Yi Wang
Yi QinYi Qin
Yi Qin
BTBaoping Tang
Baoping Tang
The vibration signals collected from aero-engine accessory casing suffer from serious background noise and strong harmonic interference caused by a combination of nonstationary operating conditions, complex transmission paths, and time-varying airflow environments, which ultimately lead to weak early fault signature information. In recent years, blind deconvolution is considered as a very powerful approach for weak signal detection and attracted much attention in dynamic signal processing area. Moreover, when suppressing the above interference, the traditional blind deconvolution (TBD) method exists the issue of manually solving the filter coefficients, which leads to extraction errors. In order to solve the aforementioned issues, an aero-engine accessory casing weak fault signature mining method based on adaptive global noise suppression (AGNS) deep deconvolution is proposed. First, a noise suppression deep convolution network is constructed as an AGNS deep deconvolution model, and an adaptive fault period block operator is established by utilizing the autocorrelation function to match with the fault period, which is used to perform the adaptive block operation of aero-engine accessory casing vibration signals. Then, a global noise energy amplitude ratio loss function is constructed as the objective function of the AGNS deep deconvolution, which is solved by iterative optimization of the filter coefficients by utilizing the Adam optimization algorithm, so as to gradually suppress the background noise interference and the strong harmonic interference components in the vibration signals of the aero-engine accessory casing. Finally, the effectiveness and generalization of the AGNS deep deconvolution method are verified by utilizing a rolling bearing outer race fault simulated signal under heavy background noise and strong harmonic interference and an aero-engine accessory casing vibration signal under real operating conditions, which indicates that the AGNS deep deconvolution method has the capability of detecting weak faults in the aero-engine accessory casing while comparing it with the latest reported TBD method, which demonstrates that the AGNS deep deconvolution method is superior to the latest reported TBD method, especially in terms of the ability of detecting weak faults in the aero-engine accessory casing.