To accurately diagnose the quayside container crane (QCC) gearbox faults, this article proposes a method that combines the frequency-domain Markov transformation field (FDMTF) and multi-branch residual convolutional neural network (MBRCNN). Firstly, the gearbox vibration signal is converted into the frequency domain to reveal the components and amplitude of signals stably and concisely. Then, the one-dimensional frequency signal is encoded into the two-dimensional image by the Markov transformation field to capture the dynamic characteristics of signals. Thirdly, the MBRCNN network is constructed, which can extract multi-scale features and alleviate the problems caused by the deep network structure. Finally, the FDMTF image is fed into the constructed MBRCNN model for pattern recognition. The effectiveness of the proposed FDMTF–MBRCNN method is verified by two case studies. In Case 1, the diagnosis results of a benchmark dataset achieve 100% accuracy, better than seven state-of-the-art methods published in recent 3 years. In Case 2, the diagnosis results of the dataset collected from a 1:4 scaled test rig achieve 98.85% accuracy, better than eleven encoding methods and four convolutional neural network methods. It also can obtain a recognition accuracy of more than 94% under the conditions of small sample, different network hyper-parameters, or variable loads, which verifies its robustness. These case studies show that the FDMTF–MBRCNN method is expected to be applied to the actual fault diagnosis of QCC gearboxes.
19 January 2023 in IEEE Transactions on Instrumentation and Measurement
Structural damage detection plays an important part in structural health monitoring for engineering structures. However, monitored signals are easily polluted by noise and the damaged data are difficult to obtain. In this work, a novel structural damage detection approach using multi-sensor spatial-temporal graph-based features and deep graph convolutional networks (DGCN) is presented. The spatial-temporal graph is constructed by graph theory based on continuous wavelet transform (CWT) of vibration signals. Then the multi-sensor spatial-temporal graph-based feature is extracted based on the Laplacian matrix derived from the spatial-temporal graph of the multi-sensor data. To overcome the limitation of small data size which obstructed the use of the artificial neural network and convolutional neural network, a deep graph convolutional network is utilized to classify the damage type of the monitored structure. The extracted multi-sensor spatial-temporal graph-based feature vector is used to represent the node of the global graph as the input of the DGCN. The node with the same condition of the structure can be classified by using the well-trained DGCN. Experiments of the IASC-ASCE SHM benchmark structure and Qatar steel frame structure in the laboratory are performed to verify the effectiveness of the proposed approach. The experimental results show that the DGCN method can be used to detect structural damage by learning from the constructed global graphs. Comparative experiments demonstrating that the proposed approach performs better than the conventional approach, especially for the limited dataset and noise polluted case.
25 February 2022 in Measurement Science and Technology
Weak fault detection is a complex and challenging task when two or more faults (i.e. a compound fault) with discordant severity occur in different parts of a gearbox. The weak fault features are prone to be submerged by the severe fault features and strong background noise, which easily lead to a missed diagnosis. To solve this problem, a novel diagnosis method combining multi-symplectic geometry mode decomposition (MSGMD) and multipoint optimal minimum entropy deconvolution adjusted (MOMEDA) is proposed for gearbox compound fault in this paper. Specifically, different fault components are separated by an improved symplectic geometry mode decomposition (SGMD), namely the MSGMD method. The weak fault features are enhanced by the MOMEDA. In the process of research, a new scheme of selecting the key parameters for MOMEDA is proposed, which is a key step in the practical application of MOMEDA. Compared with SGMD, the proposed MSGMD has two main improvements, including suppressing mode mixing and preventing the generation of pseudo-components. Compared with the original method of selecting parameters based on multipoint kurtosis, the proposed MOMEDA parameter-selecting scheme has the merits of higher accuracy and greater precision. The analysis results of two cases, of simulation and an experiment signal, reveal that the MSGMD–MOMEDA method can accurately diagnose gearbox compound fault even under strong background noise.
2 January 2021 in Mathematical and Computer Modelling of Dynamical Systems
This research presents the mathematical modelling of kinematic and complete dynamic analysis of a novel over-constrained parallel mechanism, which consists of two universal-prismatic-revolute joint limbs and one revolute-revolute-universal joint limb. The kinematic model is constructed based on the closed-loop vector method and the velocity Jacobian matrix is deduced, velocity-mapping relationships between all moving components and moving platform are also performed. Afterwards, inertia and applied forces are analysed, the complete dynamic equations with the classical Stribeck friction model of the proposed structure is established based on the principle of virtual work. A theoretical numerical example is given to solve kinematics and dynamics solutions, and theoretical forces from developed dynamic formulation are verified by the physic model simulation in Simscape and the rigid-flexible coupling model simulation in Adams. A good agreement between the theoretical results and multi-body software simulation is found.
1 January 2017 in Mathematical Problems in Engineering
The fatigue crack growth (FCG) phenomenon generally exists in large mechanical structures. Due to the influences of varied kinds of random factors, the safety evaluation of structure in FCG is under great uncertainty. In this paper, based on the reliability theory, the limit state equations of fracture failure and static strength failure were derived firstly, and the parameters in those equations were regarded as random variables that follow the normal distribution or log‐normal distribution. According to the limit state equations, the JC method (equivalent normalizing method) was used to calculate the reliability indexes under the different failure modes of structure in every stress cycle. Based on the reliability indexes and correlation of the two failure modes, the joint failure probability was obtained. In the end, a specific computation example was given, and the curve of joint failure probability in multiple failure modes was used for comparison with the result of single failure mode. The results indicated that the reliability analysis based on multiple failure modes was more reasonable, and the evaluation of reliability could be obtained in fatigue crack growth process.