JVE International
Not a member yet
1200 research outputs found
Sort by
Life prediction method of rolling bearing based on CNN-LSTM-AM
Bearing is the key component to determine the health of machinery, and it is of great significance to monitor its working status in real time and predict its remaining useful life. In recent years, the RUL prediction method based on deep learning has been widely used and achieved good prediction results. Here, a bearing life prediction method based on convolution neural network (CNN), long short term memory (LSTM) and attention mechanism (AM) is proposed. First of all, the time domain and frequency domain features of the original vibration signals of rolling bearings are extracted, and the extracted feature set is normalized as the input of CNN. The main function of CNN is to extract spatial features and reduce the dimension of the data. Then, using LSTM to extract the information that may be ignored by CNN, the feature information extracted by CNN-LSTM is input to the attention mechanism for weighting, and the key information is screened. And then more accurately represent the degradation characteristics of the equipment, and finally get the bearing remaining life. The performance of the model is verified by two sets of public data sets, and the experimental results show that it is compared with the CNN-LSTM method. The root mean square error (RMSE) index based on CNN-LSTM-AM method is reduced by 14.6 % and 13.8 % respectively, and the score index is increased by 2.0 % and 2.4 % respectively. The results show that the proposed method has higher accuracy in bearing RUL prediction
Editorβs Letter. Malocclusion treatment tools evolution β electromagnetic synergism. What is the current status of knowledge? Part I
Noise control of audio recognition equipment for multimedia system
Noise control is one of the most critical technical indicators to improve the performance of intelligent audio recognition system. Based on the noise cancellation technology, a distributed low noise amplification circuit design was proposed, and the PE15-0P technology was applied to realize broadband low noise amplification. The amplifier circuit used diodes and resistors for voltage division, which effectively achieved bias saturation at the transistor and then diode structure. According to the design of low noise amplifier, the noise output characteristics were simulated and analyzed. An audio enhancement method based on noise type recognition was proposed, which can optimize noise estimation by selecting parameter combinations according to noise type, so as to improve the quality and intelligibility of noise frequency signals in various noise environments. From the aspects of hardware and algorithm design, the noise signal was comprehensively reduced, and the accuracy of audio recognition was significantly improved
Problems of rutting on asphalt pavements
In the article, under field conditions (on the lane of a city road for public transport), using modeling and traffic flow analysis methods, the formation of ruts on an asphalt concrete pavement is studied. The maximum total rut depth on the road section under consideration reaches 110 mm. 715 buses and 25 trucks pass along a separate lane of the road per day, the relative rutting impact of which is from 5.68 to 16.41 compared to the design vehicle. The design of the road pavement on the experimental section with a total thickness of 48 cm is too weak for the actual traffic flow, which was the main reason for the premature failure of the road due to unacceptable rut sizes on the asphalt concrete pavement
Simulation analysis of helicopter rotor blade based on fluid-structure coupling
Since the helicopters are required to fulfil many different attitudes during actual flight and are exposed to low amplitude and high number of cycles of vibration loads for a long period of time, the stresses on its rotor structure will be more complicated, which will lead to the rotor blades being subjected to larger stresses and causing fatigue damage. This paper proposes a combination of fluid-solid coupling and nCode fatigue simulation of helicopter rotor blade structure to study the stress distribution, danger point and fatigue life of rotor blades in hovering and forward flight state, so as to provide a reference basis for the judgement of helicopter rotor blade fatigue damage and the enhancement of safety performance. The results show that the maximum stress of the helicopter in the forward flight state is larger than that in the hovering state, and the maximum stress of the rotor blade in the forward flight state of the helicopter is located at the root of the blade as 166.89 MPa; and the fatigue life in the two states is obtained by the joint simulation method of Workbench-nCode, and the fatigue life in the forward flight state is reduced by 0.726 % compared with that in the hovering state. Therefore, the combined method of fluid-solid coupling and nCode fatigue simulation proposed in this paper can provide an effective research method for the design and optimisation process of helicopter rotor blades
Method of experimental determination of the effective area of a pneumatic spring of high-speed rolling stock
The object of research is a pneumatic spring of high-speed rolling stock of the railway. The method of experimental static testing of a pneumatic spring of high-speed rolling stock is presented. Based on experimental tests, the βforce-strainβ dependences of a pneumatic spring are obtained when the pressure gauge in the pneumatic spring changes from 2.5 atm up to 5.0 atm. Using a thermodynamic model, a quadratic equation is found to determine the effective area of a pneumatic spring. It is established that when the pressure gauge in the pneumatic spring changes from 2.5 atm up to 5.0 atm the effective area of the pneumatic spring varies from 0.231 m2 to 0.306 m2. The scientific novelty lies in the fact that for the first time, on the basis of static experiments, the change in the effective area of the pneumatic spring of high-speed rolling stock depending on the value of the gauge pressure in the spring was established. This will make it possible to determine the forces acting on the pneumatic spring in different operating conditions, ensuring the required level of safety of rolling stock
Common fixed-point theorem for commuting maps on a metric space
Several novel uses of theorems for fixed points in commuting mapping in a fully metric domain are presented. Several conclusions from full metric fixed point theory are improved and extended by our work. Our proofs are inspired by the study of commuting mappings [B. Fisher and S. Sessa, on a fixed point theorem of Gregus, 1986] and [P. Sumati Kumari, Fixed and periodic point theory in certain spaces, 2013]
JTC online comprehensive fault diagnosis method based on angle feature and linear trend feature
Aiming at the problem of incompatibility of the fault diagnosis method between JTC (Jointless Track Circuit) compensation capacitor and tuning zone, based on the amplitude envelope mathematical model of induced voltage of locomotive signal, an online comprehensive fault diagnosis algorithm for multi-compensation capacitor and tuning equipment fault was proposed. It is characterized by the angle of the tangent vector of the amplitude envelope at the compensation capacitor and the linear trend within the three compensation capacitor sections close to the transmitter when the tuning device fails, the angle feature and linear trend feature are extracted to determine the fault type. Experimental results show that the proposed algorithm can accurately detect multi-compensation capacitor faults and tuning equipment faults with high accuracy and high efficiency, especially the sudden multi-compensation capacitor faults and tuning zone unit breaking faults. The accuracy of the algorithm for JTC fault diagnosis is verified under different signal-to-noise ratio and ballast resistance fluctuation, which shows that the algorithm has strong applicability
Analysis of a bus vertical dynamic performances β a comparison between linear and nonlinear suspension systems
This paper mainly focuses on the numerical calculation to determine the vertical evaluation indexes with all three types of typical harmonic, transient and random road excitations. The effects of linear and nonlinear suspension characteristics on the vertical evaluation indexes are fully understood systematically. The ride comfort, suspension working space, and road holding are analyzed for both two cases of linear and nonlinear suspension systems. The improvement of the vertical stability and road holding in the case of nonlinear suspension subjected under three different excitations could be characterized most meaningfully. The obtained results help to systematically get full understanding of the investigated problem nature. It also should guide interested readers in suspension design to improve the stability, safety, and ride comfort of buses
Analytical determination of critical velocity and frequencies of beam with moving mass under different supporting conditions
For a moving mass-beam system, the critical velocity of the moving mass is a key parameter that relates to the vibration stability of the system. In fact, the critical velocity obtained by the commonly used assumed mode method (AMM) differs from the actual situation. In this study, an analytical procedure is introduced to determine the critical velocity and frequency of the moving mass-beam system. The influence of moving mass is considered in the modal functions of the beam, and the frequency equations of the system were obtained through the modal analysis method and Laplace transform. And beams with four types of boundary condition were analyzed, which are hinged-hinged (HH) beam, clamped-hinged (CH) beam, clamped-clamped (CC) beam, and cantilever (CF) beam. By solving the frequency equations, the vibration frequencies of the system can be obtained, and the critical velocity can be determined. The results of the proposed method were validated by the finite element method (FEM). Through some examples, it was found that the natural frequency and critical velocity obtained by AMM is relatively high. And the critical velocities of the same moving mass-beam system under different supporting conditions ranked in ascending order are as follows: vcrHH<vcrCH<vcrCF<vcrCC. It is also found that when the moving mass undergoes variable motion on a beam, the vibration frequency obtained with acceleration considered is higher than that obtained with acceleration neglected. The results of this article will be helpful for structural design and its dynamic analysis