The vast majority of the existing diagnostic studies using deep learning techniques for rotating machinery focus on the vibration analysis under steady rotating speed. Nevertheless, the collected ...vibration signals are sensitive to time-varying speeds and the vibration sensors may cause structure damage of equipment after long-term close contact. Aiming at these aforementioned problems, a modified Gaussian convolutional deep belief network driven by infrared thermal imaging is proposed to automatically diagnose different faults of rotor-bearing system under time-varying speeds. First, infrared thermal images are measured to characterize the working states of rotor-bearing system to reduce the impact of changeable speeds. Second, Gaussian units are used to construct Gaussian convolutional deep belief network to well deal with infrared thermal images. Finally, trackable learning rate is designed to modify the training algorithm to enhance the performance. The comparison results verify the feasibility of the proposed method, which outperforms the other methods.
Classification of faults in mechanical components using machine learning is a hot topic in the field of science and engineering. Generally, every real-world running mechanical system exhibits ...personalized vibration behaviors that can be measured with acceleration sensors. However, faulty samples of such systems are difficult to obtain. Therefore, machine learning methods, such as support vector machine (SVM), neural network (NNs), etc., fail to obtain agreeable fault detection results through smart sensors. A personalized diagnosis fault method is proposed to activate the smart sensor networks using finite element method (FEM) simulations. The method includes three steps. Firstly, the cosine similarity updated FEM models with faults are constructed to obtain simulation signals (fault samples). Secondly, every simulation signal is separated into sub-signals to solve the time-domain indexes to generate the faulty training samples. Finally, the measured signals of unknown samples (testing samples) are inserted into the trained SVM to classify faults. The personalized diagnosis method is applied to detect bearing faults of a public bearing dataset. The classification accuracy ratios of six types of faults are 90% and 92.5%, 87.5% and 87.5%, 85%, and 82.5%, respectively. It confirms that the present personalized diagnosis method is effectiveness to detect faults in the absence of fault samples.
Intelligent fault diagnosis of roller bearings is facing two important problems, one is that train and test datasets have the same distribution, and the other is the installation positions of ...accelerometer sensors are limited in industrial environments, and the collected signals are often polluted by background noise. In the recent years, the discrepancy between train and test datasets is decreased by introducing the idea of transfer learning to solve the first issue. In addition, the non-contact sensors will replace the contact sensors. In this paper, a domain adaption residual neural network (DA-ResNet) model using maximum mean discrepancy (MMD) and a residual connection is constructed for cross-domain diagnosis of roller bearings based on acoustic and vibration data. MMD is used to minimize the distribution discrepancy between the source and target domains, thereby improving the transferability of the learned features. Acoustic and vibration signals from three directions are simultaneously sampled to provide more complete bearing information. Two experimental cases are conducted to test the ideas presented. The first is to verify the necessity of multi-source data, and the second is to demonstrate that transfer operation can improve recognition accuracy in fault diagnosis.
Display omitted
•A dynamic model of an axial piston pump is developed and experimentally validated.•Influences of operating conditions on the vibrations are studied.•Influences of stiffness and ...damping coefficients on the vibrations are studied.•The amplitude-frequency vibration responses and phase trajectory plots are analyzed.•Complex irregular motions occur under different working conditions.
A dynamic model with four masses and 19 degree of freedoms is proposed to investigate the vibration response characteristics of an axial piston pump. In the model, main parts are simplified by multiple lumped mass points connected with spring-damper elements. Experimental investigation is performed, and the discharge dynamic pressures and vibrations are measured to validate the dynamic model. Using the constructed model, influences of operating conditions (the discharge pressure, the rotational speed, and the displacement angle), and stiffness and damping coefficients between different contacting surfaces (the cylinder and valve plate, the piston and cylinder bore, and the slipper and swash plate) on the amplitude-frequency vibration responses and phase trajectory plots are analyzed. The findings showed that the vibration responses are significantly affected by the operating conditions, and are also considerably affected by the stiffness and damping coefficients. The rotational speed determines the fundamental frequency and its harmonics, and most of the harmonic vibration responses increase with increasing discharge pressure and displacement angle. The shape and the area defined by the phase trajectory are significantly changed by the operating conditions. The complex irregular motion might be changed into less irregular motion with decreasing discharge pressure, rotational speed and displacement angle.
: When a structure is subjected to dynamic or static loads, cracks may develop and the modal shapes and frequencies of the cracked structure may change accordingly. Based on this, a new method is ...proposed to locate beam cracks and to estimate their depths. The fault‐induced modal shape and frequency changes of cracked structures are taken into account to construct a new hybrid crack detection method. The method includes two steps: crack localization and depth estimation. The locations of the cracks are determined by applying the wavelet transform to the modal shape. Using the measured natural frequencies as inputs, the depths of the cracks are estimated from a database established by wavelet finite element method. The effectiveness of the proposed hybrid two‐step method is demonstrated by numerical simulation and experimental investigation of a cantilever beam with two cracks. Our analyses also indicate that the proposed method performed reasonably well at certain level of noise.
Time-frequency ridge not only exhibits the variable process of non-stationary signal with time changing but also provides the information of signal synchronous or non-synchronous components for ...subsequent detection research. Consequently, the key is to decrease the error between real and estimated ridge in the time-frequency domain for accurate detection. In this article, an adaptive weighted smooth model is presented as a post-processing tool to refine the time-frequency ridge which is based on the coarse estimated time-frequency ridge using newly emerging time-frequency methods. Firstly, the coarse ridge is estimated by using multi-synchrosqueezing transform for vibration signal under variable speed conditions. Secondly, an adaptive weighted method is applied to enhance the large time-frequency energy value location of the estimated ridge. Then, the reasonable smooth regularization parameter associated with the vibration signal is constructed. Thirdly, the majorization-minimization method is developed for solving the adaptive weighted smooth model. Finally, the refined time-frequency characteristic is obtained by utilizing the stop criterion of the optimization model. Simulation and experimental signals are given to validate the performance of the proposed method by average absolute errors. Compared with other methods, the proposed method has the highest performance in refinement accuracy.
This paper aims to propose a wavelet boundary element method (WBEM) to study the three-dimensional elasticity problem and potential problem. In contrast with conventional polynomial interpolation in ...the BEM, the scaling functions of the B-spline wavelet on the interval (BSWI) are applied to derive calculated formats of the WBEM, construct BSWI elements, discretize the geometric shape, and form BSWI BEM algebraic equations. Because BSWI scaling functions have specific expressions, the integration related to scaling functions can be evaluated directly without other complicated calculation steps like applying other wavelet bases. The Gauss quadrature scheme based on the background cell is implemented to evaluate the integration involved in the WBEM. Furthermore, the singular integration problem appearing in the WBEM can be transformed into that appearing in traditional BEM to solve. Unlike the WBEM in the published literature, arbitrary boundary conditions can be solved directly as the wavelet-based elements are employed to discrete the geometry of structures. Some typical examples with several boundary conditions are provided to verify this method. The numerical solutions illustrate the good convergence, reliability, and flexibility of WBEM by comparison with the traditional BEM and exact solutions.
Using the piezoelectric (PZT) effect, energy-harvesting has become possible for phononic crystal (PnC). Low-frequency vibration energy harvesting is more of a challenge, which can be solved by local ...resonance phononic crystals (LRPnCs). A novel three-dimensional (3D) energy harvesting LRPnC is proposed and further analyzed using the finite element method (FEM) software COMSOL. The 3D LRPnC with spiral unit-cell structures is constructed with a low initial frequency and wide band gaps (BGs). According to the large vibration deformation of the elastic beam near the scatterer, a PZT sheet is mounted in the surface of that beam, to harvest the energy of elastic waves using the PZT effect. To further improve the energy-harvesting performance, a 5 × 5 super-cell is numerically constructed. Numerical simulations show that the present 3D super-cell PnC structure can make full use of the advantages of the large vibration deformation and the PZT effect, i.e., the BGs with a frequency range from 28.47 Hz to 194.21 Hz with a bandwidth of 142.7 Hz, and the maximum voltage output is about 29.3 V under effective sound pressure with a peak power of 11.5 µW. The present super-cell phononic crystal structure provides better support for low-frequency vibration energy harvesting, when designing PnCs, than that of the traditional Prague type.
Bearing, an importunate component of any rotary machinery, is jeopardized to its failure during its operation in tough working conditions. The condition monitoring of bearing, to avoid its unforeseen ...failure, is important for its smooth working. Bearing damage assessment is mostly done by selecting features from the vibration signals, which is usually, a time consuming process. Consequently, it becomes importunate for us to achieve full automation for the safety purpose and reduction in the maintenance cost of the machinery. Towards this omnifarious effort, a wavelet transformed based Deep Convolutional Neural Network (DCNN) is proposed for the automatic identification of defective components and damage assessment of bearing, which is achieved by, firstly, processing vibration signals using continuous wavelet transform to form 2D grey scale images of time-frequency representation. Secondly, DCNN is trained using images for learning of defects severity. Through convolution and pooling operation layers, high level features are automatically extracted from images itself. Thereafter, trained 2D grey images are applied to DCNN so that defect severity assessment can be accurately carried out. The overall accuracy achieved using the proposed method is 100%.
Hydraulic multi-way valves as core components are widely applied in engineering machinery, mining machinery, and metallurgical industries. Due to the harsh working environment, faults in hydraulic ...multi-way valves are prone to occur, and the faults that occur are hidden. Moreover, hydraulic multi-way valves are expensive, and multiple experiments are difficult to replicate to obtain true fault data. Therefore, it is not easy to achieve fault diagnosis of hydraulic multi-way valves. To address this problem, an effective intelligent fault diagnosis method is proposed using an improved Squeeze-Excitation Convolution Neural Network and Gated Recurrent Unit (SECNN-GRU). The effectiveness of the method is verified by designing a simulation model for a hydraulic multi-way valve to generate fault data, as well as the actual data obtained by establishing an experimental platform for a directional valve. In this method, shallow statistical features are first extracted from data containing fault information, and then fault features with high correlation with fault types are selected using the Maximum Relevance Minimum Redundancy algorithm (mRMR). Next, spatial dimension features are extracted through CNN. By adding the Squeeze-Excitation Block, different weights are assigned to features to obtain weighted feature vectors. Finally, the time-dimension features of the weighted feature vectors are extracted and fused through GRU, and the fused features are classified using a classifier. The fault data obtained from the simulation model verifies that the average diagnostic accuracy of this method can reach 98.94%. The average accuracy of this method can reach 92.10% (A1 sensor as an example) through experimental data validation of the directional valve. Compared with other intelligent diagnostic algorithms, the proposed method has better stationarity and higher diagnostic accuracy, providing a feasible solution for fault diagnosis of the hydraulic multi-way valve.