For the sake of solving the problem of the difficulty of extracting fault features under the background of noise and accurately identify the state of the bearing, a compound fault diagnosis method of rolling bearing based on parameter optimization maximum correlated kurtosis deconvolution (MCKD) and convolutional neural network (CNN) is proposed. First, the adaptive multi-strategy cuckoo search algorithm (MSACS) is used to iteratively optimize the important parameters of MCKD. Second, the optimized MCKD is used to filter and denoise the rolling bearing fault signal, and the denoised signal is obtained. Finally, the denoised signal is input to the CNN model for training and testing to obtain the classification result of fault diagnosis. Through the test and evaluation of the fault dataset, the proposed method is compared with particle swarm optimization (PSO) parameter optimization method (PSO-MCKD-CNN) and CNN method without noise reduction. At the same time, it is compared with other advanced methods. The experimental results shows that this method improves the diagnostic performance of the neural network, obtains higher diagnostic accuracy, and is more conducive to the detection of compound faults.

Considering the nonlinear and nonstationary characteristics of rolling bearing vibration signals, we propose a rolling bearing fault diagnosis method based on complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN), refined composite multiscale fuzzy entropy (RCMFE), Laplace score (LS), and the particle swarm optimization-probabilistic neural network (PSO-PNN). First, the method employs CEEMDAN to decompose the vibration signal and select the intrinsic mode functions (IMFs) containing the primary fault information via the frequency-domain correlation coefficient method. Then, it uses RCMFE to extract the characteristic information from the selected IMF. In addition, it uses LS to select and construct low-dimensional sensitive feature vectors, which are incorporated into the PSO-PNN model for diagnostic analysis to realize the state recognition of rolling bearing. Finally, the effectiveness of the method is verified by the analysis of the experimental data.

The paper presents a computationally efficient method for system reliability analysis of mechanisms. The reliability is defined as the probability that the output error remains within a specified limit in the entire target trajectory of the mechanism. This mechanism reliability problem is formulated as a series system reliability analysis that can be solved using the distribution of maximum output error. The extreme event distribution is derived using the principle maximum entropy (MaxEnt) along with the constraints specified in terms of fractional moments. To optimize the computation of fractional moments of a multivariate response function, a multiplicative form of dimensional reduction method (M-DRM) is developed. The main benefit of the proposed approach is that it provides full probability distribution of the maximal output error from a very few evaluations of the trajectory of mechanism. The proposed method is illustrated by analyzing the system reliability analysis of two planar mechanisms. Examples presented in the paper show that the results of the proposed method are fairly accurate as compared with the benchmark results obtained from the Monte Carlo simulations.

Medium-carbon steel is commonly used for the rail, wire ropes, tire cord, cold heading, forging steels, cold finished steel bars, machinable steel and so on. Its fatigue behavior analysis and fatigue life estimation play an important role in the machinery industry. In this paper, the estimation of fatigue life of medium-carbon steel with different surface roughness using established S-N and P-S-N curves is presented. To estimate the fatigue life, the effect of the average surface roughness on the fatigue life of medium-carbon steel has been investigated using 75 fatigue tests in three groups with average surface roughness (R_a): 0.4 μm, 0.8 μm, and 1.6 μm, respectively. S-N curves and P-S-N curves have been established based on the fatigue tests. The fatigue life of medium-carbon steel is then estimated based on Tanaka-Mura crack initiation life model, the crack propagation life model using Paris law, and material constants of the S-N curves. Six more fatigue tests have been conducted to validate the presented fatigue life estimation formulation. The experimental results have shown that the presented model could estimate well the mean fatigue life of medium-carbon steel with different surface roughness.