In the rolling bearing fault diagnosis, the vibration signal of single sensor is usually nonstationary and noisy, which contains very little useful information, and impacts the accuracy of fault diagnosis. In order to solve the problem, this paper presents a novel fault diagnosis method using multivibration signals and deep belief network (DBN). By utilizing the DBN’s learning ability, the proposed method can adaptively fuse multifeature data and identify various bearing faults. Firstly, multiple vibration signals are acquainted from various fault bearings. Secondly, some time-domain characteristics are extracted from original signals of each individual sensor. Finally, the features data of all sensors are put into the DBN and generate an appropriate classifier to complete fault diagnosis. In order to demonstrate the effectiveness of multivibration signals, experiments are carried out on the individual sensor with the same conditions and procedure. At the same time, the method is compared with SVM, KNN, and BPNN methods. The results show that the DBN-based method is able to not only adaptively fuse multisensor data, but also obtain higher identification accuracy than other methods.

Mechanical fault diagnosis is an important method to accurately identify the health condition of mechanical equipment and ensure its safe operation. With the advent of the era of ‘big data’, it is an inevitable trend to choose deep learning for mechanical fault diagnosis. At the same time, to improve the generalization ability of deep learning applications in different scenarios of fault diagnosis, mechanical diagnosis based on transfer learning has also been proposed and become an important branch in the field of mechanical fault diagnosis. This paper introduces the principle of transfer learning, summarizes the research and application of transfer learning in the field of fault diagnosis, discusses the shortcomings of transfer learning in the field of fault diagnosis, and discusses the future research direction of transfer learning in the field of fault diagnosis.

The dynamic response of the vibrating screen has a great impact on the screening efficiency and fatigue life of the structures. For the conventional dynamic design, the consideration of the influence of load weight on dynamic response is lacking. So, in this paper, taking a very common vibrating screen used in tunnel construction as an example, the relationship between the screen dynamic response and the load weight is studied through numerical simulations. Firstly, to make sure the accuracy of simulation, the three‐dimensional finite element model of a vibration screen is strictly built to maximize consistency with the real screen, and then the simulated results are validated by experiments. Furthermore, the variation regularity of dynamic response with the load weight and excitation frequency is analyzed based on simulations. Results show the load weight has obvious influence on the modal shapes as well as the natural frequencies. There are three regions that will lead to the sudden increase of vibration acceleration: (1) the load weight variates within 0–50 kg and excitation frequency variates within 40–60 Hz; (2) the load weight variates within 10–100 kg and excitation frequency variates within 50–90 Hz; (3) the load weight variates within 80–200 kg and excitation frequency variates within 70–100 Hz. These results will provide new theoretical reference for the maintenance and further improvement in the dynamic design of the vibrating screen.

A spiral‐bevel gear is a basic transmission component and is widely used in mechanical equipment; thus, it is important to monitor and diagnose its running state to ensure safe operation of the entire equipment setup. The vibration signals of spiral‐bevel gears are typically quite complicated, as they present both nonlinear and nonstationary characteristics and are interfered with by strong noise. The complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) method has been proven to be an effective method for analyzing this kind of signal. However, the fault feature information after CEEMDAN is not obvious and needs to be quantified. Permutation entropy can be used to quantify the randomness, complexity, and mutation of vibration time‐series signals. This paper proposes to take the CEEMDAN‐based permutation entropy as the sensitive feature for spiral‐bevel gear fault identification. First, the raw vibration signal is decomposed by the CEEMDAN method to obtain a series of intrinsic modal functions (IMFs). The IMFs which included greater amounts fault information are selected as the optimal IMFs based on the correlation coefficient. Next, the permutation entropy values of the optimal IMFs are calculated. In order to obtain accurate permutation entropy values, the two key parameters, namely, embedding dimension and delay time, are optimized by using the overlapping parameter method. In order to assess the sensibility of the permutation entropy features, the support vector machine (SVM) is used as the classifier for fault mode identification, and the diagnostic accuracy can verify its sensibility. The permutation entropy of CEEMDAN‐based/EEMD‐based/EMD‐based features, combined with SVM, is applied to identify three different fault modes of spiral‐bevel gears. Their respective diagnostic accuracies are 100%, 88.33%, and 83.33%, which indicate that the CEEMDAN‐based permutation entropy is the most sensitive feature for the fault identification of spiral‐bevel gears.

Aiming at the difficulty of rolling bearing fault diagnosis in a strong noise environment, this paper proposes an enhanced integrated filter network. In the method, we firstly design an enhanced integrated filter, which includes the filter enhancement module and the expression enhancement module. The filter enhancement module can not only filter the high-frequency noise to extract useful features of medium and low-frequency signals but also maintain frequency and time resolution to some extent. On this basis, the expression enhancement module analyzes fault features intercepted by the upper network at multiple scales to get deep features. Then we introduce vector neurons to integrate scalar features into vector space, which mine the correlation between features. The feature vectors are transmitted by dynamic routing to establish the relationship between low-level capsules and high-level capsules. In order to verify the diagnostic performance of the model, CWRU and IMS bearing datasets are used for experimental verification. In the strong noise environment of SNR = −4 dB, the fault diagnosis precisions of the method on CWRU and IMS reach 94.85% and 92.45%, respectively. Compared with typical bearing fault diagnosis methods, the method has higher fault diagnosis precision and better generalization ability in a strong noise environment.

The finite element model of a dual-rotor system was established by Timoshenko beam element. The dual-rotor system is a coaxial rotor whose supporting structure is similar to that of an aero-engine rotor system. The inner rotor is supported by three bearings, which makes it a redundantly supported rotor. The outer rotor connects the inner rotor by an intershaft bearing. The spectrum characteristics of the dual-rotor system under unbalanced excitation and misalignment excitation were analysed in order to study the influence of coupling misalignment of the inner rotor on the spectral characteristics of the rotor system. The results indicate that the vibration caused by the misaligned coupling of the inner rotor will be transmitted to the outer rotor through the intershaft bearing. Multiple harmonic frequency components, mainly 1x and 2x, will be excited by the coupling misalignment. The amplitudes of all harmonic frequencies increase with the misalignment in both the inner and outer rotors. The vibration level of the outer rotor affected by the misalignment is lower than that of the inner rotor because it is far from the misaligned coupling. Harmonic resonance occurs when any harmonic frequencies of the misalignment response coincide with a natural frequency of the system. In order to verify the theoretical model, experiments are performed on a test rig. Both the experimental and simulation results are in good accordance with each other.