Continual learning fault diagnosis:A dual-branch adaptive aggregation residual network for fault diagnosis with machine increments

As a data-driven approach, Deep Learning(DL)-based fault diagnosis methods need to collect the relatively comprehensive data on machine fault types to achieve satisfactory performance. A mechanical system may include multiple submachines in the real-world. During condition monitoring of a mechanical system, fault data are distributed in a continuous flow of constantly generated information and new faults will inevitably occur in unconsidered submachines, which are also called machine increments. Therefore, adequately collecting fault data in advance is difficult. Limited by the characteristics of DL, training existing models directly with new fault data of new submachines leads to catastrophic forgetting of old tasks, while the cost of collecting all known data to retrain the models is excessively high. DL-based fault diagnosis methods cannot learn continually and adaptively in dynamic environments. A new Continual Learning Fault Diagnosis method(CLFD) is proposed in this paper to solve a series of fault diagnosis tasks with machine increments. The stability–plasticity dilemma is an intrinsic issue in continual learning. The core of CLFD is the proposed Dual-branch Adaptive Aggregation Residual Network(DAARN).Two types of residual blocks are created in each block layer of DAARN: steady and dynamic blocks. The stability–plasticity dilemma is solved by assigning them with adaptive aggregation weights to balance stability and plasticity, and a bi-level optimization program is used to optimize adaptive aggregation weights and model parameters. In addition, a feature-level knowledge distillation loss function is proposed to further overcome catastrophic forgetting. CLFD is then applied to the fault diagnosis case with machine increments. Results demonstrate that CLFD outperforms other continual learning methods and has satisfactory robustness.

Iterative HOEO fusion strategy:a promising tool for enhancing bearing fault feature

As parameter independent yet simple techniques,the energy operator(EO)and its variants have received considerable attention in the field of bearing fault feature detection.However,the performances of these improved EO techniques are subjected to the limited number of EOs,and they cannot reflect the non-linearity of the machinery dynamic systems and affect the noise reduction.As a result,the fault-related transients strengthened by these improved EO techniques are still subject to contamination of strong noises.To address these issues,this paper presents a novel EO fusion strategy for enhancing the bearing fault feature nonlinearly and effectively.Specifically,the proposed strategy is conducted through the following three steps.First,a multi-dimensional information matrix(MDIM)is constructed by performing the higher order energy operator(HOEO)on the analysis signal iteratively.MDIM is regarded as the fusion source of the proposed strategy with the properties of improving the signal-to-interference ratio and suppressing the noise in the low-frequency region.Second,an enhanced manifold learning algorithm is performed on the normalized MDIM to extract the intrinsic manifolds correlated with the fault-related impulses.Third,the intrinsic manifolds are weighted to recover the fault-related transients.Simulation studies and experimental verifications confirm that the proposed strategy is more effective for enhancing the bearing fault feature than the existing methods,including HOEOs,the weighting HOEO fusion,the fast Kurtogram,and the empirical mode decomposition.

Synchronous chirp mode extraction: A promising tool for fault diagnosis of rolling element bearings under varying speed conditions

As critical components in modern aerospace productions,rolling element bearings(REBs)generally work under varying speed conditions,which brings great challenges to their operating health monitoring.Some novel time–frequency decomposition(TFD)algorithms are established recently to extract nonlinear features from the non-stationary signals effectively,which are promising for realizing fault diagnosis of REBs under varying speed conditions.However,numerous personal experiences must be incorporated and the anti-noise performance of these methods needs to be further enhanced.Given these issues,a synchronous chirp mode extraction(SCME)-based REB fault diagnosis method is proposed for the health monitoring of REBs under varying speed conditions in this study.It mainly consists of following two parts.(a)The shaft rotational frequency(SRF)is initially estimated from the low-frequency band of the vibration signal.Simultaneously,an adaptive refining strategy is incorporated to obtain a suitable bandwidth parameter.(b)A cycle-one-step estimation frame is constructed to extract synchronous modes from the envelope waveform of the vibration signal.Meanwhile,a synchronous mode spectrum(SMS)is generated using the information of the extracted synchronous modes,which is a novel REBs fault diagnosis technique with tacholess and resampling-free.In contrast to the current TFD algorithms,the proposed method needs fewer input parameters and owns a well anti-noise performance because there is no iterative optimization in the procedure of construction of SMS.As a result,the health conditions of REBs are evaluated by detecting the exhibited features in the SMS.Simulations and experiments are conducted to validate the effectiveness of the proposed method in terms of REB fault diagnosis.Analysis results demonstrate that the proposed method outperforms the current TFD algorithm and the conventional order tracking technique for fault diagnosis of REB under varying speed conditions.

A general and simple method for evaluating the electrical transport performance of graphene by the van der Pauw–Hall measurement

Expected for many promising applications in the field of electronics and optoelectronics, a reliable method for the characterization of graphene electrical transport properties is desired to predict its device performance or provide feedback for its synthesis.However, the commonly used methods of extracting carrier mobility from graphene field effect transistor or Hall-bar is time consuming, expensive, and significantly affected by the device fabrication process other than graphene itself.Here we reported a general and simple method to evaluate the electrical transport performance of graphene by the van der Pauw–Hall measurement.By annealing graphene in vacuum to remove the adsorbed dopants and then exposing it in ambient surroundings, carrier mobility as a function of density can be measured with the increase of carrier density due to the dopant re-adsorption from the surroundings.Further, the relationship between the carrier mobility and density can be simply fitted with a power equation to the first level approximation, with which any pair of measured carrier mobility and density can be normalized to an arbitrary carrier density for comparison.We experimentally demonstrated the reliability of the method, which is much simpler than making devices and may promote the standard making for graphene characterization.

Criteria for the growth of large-area adlayer-free monolayer graphene films by chemical vapor deposition

Homogeneity is important to material applications for good performance of individual devices,for making AB-stacked bilayer graphene in a layer-by-layer stacking order,and from the point of view of industrial production.Among many properties to be controlled,for the case of graphene,the thickness(or layer number)uniformity is the prerequisite.Chemical vapor deposition(CVD)of C precursors on Cu substrates is the most popular method to produce large-area graphene films.To date,precise control on the number of graphene layers as well as the uniformity over a large area is still very challenging.In this work,with a further understanding of the factors affecting adlayer growth,the synthesis of large-area adlayer-free monolayer graphene(MLG)films was achieved up to tens of squared centimeters in area by just using untreated Cu foil and a normal CVD process.We found that keeping equal C precursor concentration on the two sides of the Cu substrate is a criterion in addition to other factors such as the ratio of H:C and the substrate surface morphology for the growth of adlayer-free MLG.This finding is not only of great significance for the industrial production of large-area adlayer-free MLG films but also instructive for the synthesis of homogeneous few-layer graphene.

卷对卷化学气相沉积法制备石墨烯

批到批(B2B)和卷到卷(R2R)工艺均可用于石墨烯薄膜的大规模生产.由于设备简单,B2B工艺在实验室研究中非常普遍.相对而言,R2R工艺更容易自动化,并且与随后的转移过程更兼容,因此在工业上更受青睐.目前,对R2R工艺的研究主要集中在反应器设计或装料结构等方面,对石墨烯生长动力学缺乏深入的了解.本文通过研究石墨烯的生长演化过程,发现在相同的反应参数下,R2R工艺的石墨烯晶畴密度大于B2B工艺的石墨烯畴密度,其原因归结于两种工艺不同的反应过程;而通过延长反应时间,可以对石墨烯薄膜的缺陷进行修复.在优化的R2R工艺下,可以获得与常规B2B工艺相当的高质量石墨烯薄膜.本工作可促进石墨烯薄膜制备技术的发展.