High-Performance Adaptive Weak Fault Diagnosis Based on the Global Parameter Optimization Model of a Cascaded Stochastic Resonance System.

Stochastic resonance (SR), as a type of noise-assisted signal processing method, has been widely applied in weak signal detection and mechanical weak fault diagnosis. In order to further improve the weak signal detection performance of SR-based approaches and realize high-performance weak fault diagnosis, a global parameter optimization (GPO) model of a cascaded SR system is proposed in this work. The cascaded SR systems, which involve multiple multi-parameter-adjusting SR systems with both bistable and tri-stable potential functions, are first introduced. The fixed-parameter optimization (FPO) model and the GPO models of the cascaded systems to achieve optimal SR outputs are proposed based on the particle swarm optimization (PSO) algorithm. Simulated results show that the GPO model is capable of achieving a better SR output compared to the FPO model with rather good robustness and stability in detecting low signal-to-noise ratio (SNR) weak signals, and the tri-stable cascaded SR system has a better weak signal detection performance compared to the bistable cascaded SR system. Furthermore, the weak fault diagnosis approach based on the GPO model of the tri-stable cascaded system is proposed, and two rolling bearing weak fault diagnosis experiments are performed, thus verifying the effectiveness of the proposed approach in high-performance adaptive weak fault diagnosis.

Stochastic Resonance with Parameter Estimation for Enhancing Unknown Compound Fault Detection of Bearings.

Although stochastic resonance (SR) has been widely used to enhance weak fault signatures in machinery and has obtained remarkable achievements in engineering application, the parameter optimization of the existing SR-based methods requires the quantification indicators dependent on prior knowledge of the defects to be detected; for example, the widely used signal-to-noise ratio easily results in a false SR and decreases the detection performance of SR further. These indicators dependent on prior knowledge would not be suitable for real-world fault diagnosis of machinery where their structure parameters are unknown or are not able to be obtained. Therefore, it is necessary for us to design a type of SR method with parameter estimation, and such a method can estimate these parameters of SR adaptively by virtue of the signals to be processed or detected in place of the prior knowledge of the machinery. In this method, the triggered SR condition in second-order nonlinear systems and the synergic relationship among weak periodic signals, background noise and nonlinear systems can be considered to decide parameter estimation for enhancing unknown weak fault characteristics of machinery. Bearing fault experiments were performed to demonstrate the feasibility of the proposed method. The experimental results indicate that the proposed method is able to enhance weak fault characteristics and diagnose weak compound faults of bearings at an early stage without prior knowledge and any quantification indicators, and it presents the same detection performance as the SR methods based on prior knowledge. Furthermore, the proposed method is more simple and less time-consuming than other SR methods based on prior knowledge where a large number of parameters need to be optimized. Moreover, the proposed method is superior to the fast kurtogram method for early fault detection of bearings.

Research on a Bearing Fault Enhancement Diagnosis Method with Convolutional Neural Network Based on Adaptive Stochastic Resonance.

As a powerful feature extraction tool, a convolutional neural network (CNN) has strong adaptability for big data applications such as bearing fault diagnosis, whereas the classification performance is limited when the quality of raw signals is poor. In this paper, stochastic resonance (SR), which provides an advanced feature enhancement approach for weak signals with strong background noise, is introduced as a data pre-processing method for the CNN to improve its classification performance. First, a multiparameter adjusting bistable Duffing system that can achieve SR under large-parameter weak signals is introduced. A hybrid optimization algorithm (HOA) combining the genetic algorithm (GA) and the simulated annealing (SA) is proposed to adaptively obtain the optimized parameters and output signal-to-noise ratio (SNR) of the Duffing system. Therefore, the data optimization based on the multiparameter-adjusting SR of Duffing system can be realized. An SR-based mapping method is further proposed to convert the outputs of the Duffing system into grey images, which can be further processed by a normal CNN with batch normalization (BN) layers and dropout layers. After verifying the feasibility of the HOA in multiparameter optimization of the Duffing system, the bearing fault data set from the CWRU bearing data center was processed by the proposed fault enhancement classification and identification method. The research showed that the weak features of the bearing signals could be enhanced significantly through the adaptive multiparameter optimization of SR, and classification accuracies for 10 categories of bearing signals could achieve 100% and those for 20 categories could achieve more than 96.9%, which is better than other methods. The influences of the population number on the classification accuracies and calculation time were further studied, and the feature map and network visualization are presented. It was demonstrated that the proposed method can realize high-performance fault enhancement classification and identification.

Nonlinear resonance decomposition for weak signal detection.

This paper attempts to investigate the behaviors of coupling stochastic resonance (CSR) subject to α-stable noise and a periodic signal by using the residence-time ratio. Then, a nonlinear resonance decomposition is designed to successfully enhance and detect weak unknown multi-frequency signals embedded in strong α-stable noise by decomposing the noisy signal into a series of useful resonant components and a residue, where the residence-time ratio, instead of the output signal-to-noise ratio and other objective functions depending on the prior knowledge of the signals to be detected, can optimize the CSR to enhance weak unknown signals. Finally, the nonlinear resonance decomposition is used to process the raw vibration signal of rotating machinery. It is found that the nonlinear resonance decomposition is able to decompose the weak characteristic signal and its harmonics, identifying the imbalance fault of the rotor. Even the proposed method is superior to the empirical mode decomposition method in this experiment. This research is helpful to design the noise enhanced signal decomposition techniques by harvesting the energy of noise to enhance and decompose the useful resonant components from a nonstationary and nonlinear signal.

Stochastic resonance subject to multiplicative and additive noise: The influence of potential asymmetries.

The influence of potential asymmetries on stochastic resonance (SR) subject to both multiplicative and additive noise is studied by using two-state theory, where three types of asymmetries are introduced in double-well potential by varying the depth, the width, and both the depth and the width of the left well alone. The characteristics of SR in the asymmetric cases are different from symmetric ones, where asymmetry has a strong influence on output signal-to-noise ratio (SNR) and optimal noise intensity. Even optimal noise intensity is also associated with the steepness of the potential-barrier wall, which is generally ignored. Moreover, the largest SNR in asymmetric SR is found to be relatively larger than the symmetric one, which also closely depends on noise intensity ratio. In addition, a moderate cross-correlation intensity between two noises is good for improving the output SNR. More interestingly, a double SR phenomenon is observed in certain cases for two correlated noises, whereas it disappears for two independent noises. The above clues are helpful in achieving weak signal detection under heavy background noise.