The induction motor is widely used for providing the running power of rotating machinery. Its fault diagnosis significant to ensure operation safety rotary Infrared thermal image analysis based on deep learning has attracted attention many researchers due its advantages in non-destructive and space locations. However, obtaining sufficient high-quality samples practical applications relatively difficult. Developing few-shot models extending engineering application analysis. existing often...

Thermal power generation undertakes more tasks of peak and frequency regulation in new systems. The load generators is complicated, significant differences exist the mechanical characteristic end winding under different loads. increasingly plays a crucial role within modern operational complexity has increased, revealing variations characteristics synchronous generator conditions. This paper proposes theoretical model for rapid calculation electromagnetic force on stator Different from...

Abstract Recently, deep learning (DL) models based on convolutional neural networks have achieved satisfactory results in rolling bearing fault diagnosis. However, the bearings usually work variable loading conditions, and their feature distribution could vary with load. The important features cannot be effectively captured convolution process using existing diagnosis models, resulting poor generalization performance. In this paper, a novel DL model, named multiscale cascade recurrent...

Abstract In practical industrial applications, rolling bearing generally operates under variable conditions and its vibration signal significantly fluctuates in amplitude frequency. This increases the feature distribution differences of fault samples makes health status identification more difficult. To this end, a new intelligent diagnosis method for time-varying speed is proposed based on time-characteristic order (TCO) spectrum multi-scale domain adaptation network (MSDAN). Firstly, by...

Deep learning based on vibration signal image representation has proven to be effective for the intelligent fault diagnosis of bearings. However, previous studies have focused primarily dealing with single-channel processing, which cannot guarantee integrity feature information. To obtain more abundant information, this paper proposes a multivariate data method, named symmetrized dot pattern (M-SDP), by combining variational mode decomposition (MVMD) (SDP). In M-SDP, signals multiple sensors...

Group-sparse mode decomposition (GSMD) is a novel signal algorithm based on the concept of group-sparse. It fast, robust against noise and has good anti-mode aliasing performance, these characteristics show that it great potential for bearing fault feature extraction. However, GSMD estimates intrinsic functions (IMFs) by set ideal filters designed energy detection over short windows. suggested susceptible to mode-splitting impact component wide bandwidth when processing signals. Therefore,...

Abstract Variational mode extraction (VME), inspired by variational decomposition (VMD), is a novel fault diagnosis technique that can efficiently extract narrowband modes from multi-component signals. Compared with VMD, VME more accurate and faster when extracting the component. However, preset center frequency ω c balance factor α seriously affect performance of VME. Therefore, spectral-coherence guided (SCVME), capable determining hyper-parameters automatically, proposed for rolling...

Abstract Rotating machinery fault signals often consist of multiple components with time varying frequencies under variable speed conditions. Spectral overlap exists among these components, making it difficult to independently separate the features components. Singular spectrum decomposition (SSD), a singular analysis-based signal method, has shown its great potential in suppressing background noise and extracting fault-related complex environments. However, SSD is frequency domain method...

Abstract Shaft voltage often exists in synchronous generators due to the assembly error or various faults after long‐term performance. The article investigates shaft characteristic under stator interturn short circuit (SISC) condition. Different from other studies, this mainly considers mapping relationship between amplitude–frequency characteristics of and SISC degrees. detailed expressions are first derived based on magnetic flux density normal condition Then finite element analysis...

Simulation models incorporating fault mechanisms can acquire sufficient samples with rich information, providing an effective solution to deep learning-driven bearing diagnosis in case of sample scarcity. However, the simulation previous studies are mainly designed for constant speed conditions and cannot generate source data aligning variable conditions. Moreover, impacts exhibit time-varying characteristics under conditions, causing obstacle feature representation learning model....

Abstract Rolling bearings are critical components in many industrial fields, and their stability directly affects the performance safety of equipment. Accurate prediction remaining useful life (RUL) rolling is a heated topic modern research. Traditional strategies unable to efficiently exploit significant features data, resulting inability determine starting time along with reduced accuracy. Accordingly, this paper proposes novel data-driven model named ConTriFormer, which incorporates...