Given local weak feature information, a novel extraction and fault diagnosis method for planetary gears based on variational mode decomposition (VMD), singular value (SVD), convolutional neural network (CNN) is proposed. VMD was used to decompose the original vibration signal components. The matrix partitioned into number of submatrices information contained in each submatrix extracted as vector using SVD. corresponding current state constructed according location submatrix. Finally, by...

Abstract A boundary enhancement and Gaussian mixture model (G) optimized synthetic minority oversampling technique (SMOTE) algorithm (BE-G-SMOTE) is proposed to improve diagnostic accuracy under imbalanced bearing fault data conditions. It designed solve the problem that diversity of samples generated by original SMOTE limited, as well deep learning limited size training processing speed. Firstly, a few are clustered G achieve cluster division. Secondly, according density distribution...

The mine water environment in underground reservoirs poses great threat to the durability of artificial concrete dams, mainly due coupled sulfate and drying-wetting cycles. As a novel response, application Engineered Cementitious Composites (ECC) featured by strain-hardening characteristics inherent crack control ability dam is proposed. special influence simulated high cycle on ECC investigated this study, measuring mass compressive properties evolvement characterizing microstructure phase...

To investigate the detailed mechanisms for lignite methanolysis, we used ReaxFF reactive force field to perform a series of molecular dynamics simulations (MDSs) on unimolecular model compound. The α-O-4 and β-O-4 types lignite-related compounds were selected as representatives linkages in lignites. reaction products predicted by MDSs are consistent with those from experimental results reported. initiation observed involving ether linkage cleavage methanol participation closely matches...

Order tracking has been widely used to diagnose failures of variable speed rotating machines. The performance the TOT (Time-Frequency Domain Tacholess Tracking) methods is based on correct separation target component strictly related shaft rotation frequency. Currently, most have focused obtaining instantaneous frequency with accuracy. In this paper, a new method proposed that combines inverse short-time Fourier transform (ISTFT) singular value decomposition (SVD). closely selected and...

Abstract As a core component of industrial robots, the RV reducer directly affects normal operation robot, so it is great significance to monitor its status and diagnose faults. In field fault diagnosis, intelligent diagnosis methods based on deep learning have shown advantages in accuracy efficiency. However, as network depth scale increase, exponentially growing model computation parameter amounts require higher hardware requirements for computers, making difficult deploy embedded...

Rolling element bearings are among the most common components in industrial rotating machinery. Condition monitoring technologies for bearing fault detection and diagnosis critical to avoid machines from productivity reduction emergency breakdown. Acoustic emission (AE) technology which detects expanding of cracks fatigued material is able monitor before visual defects formed contacting surfaces. This advantage may help AE method identify commonly used vibration does. In this paper,...

Thermal dissolution (TD) of Shengli lignite (SL) in ethyl acetate (EA) was carried out under different conditions, including temperature, solvent to SL ratio ( RS/SL), and time. The yields EA-extractable fractions (EAEFs) increased with raising temperature from 240–300°C, but then decreased when the higher than 300°C, effects RS/SL time on EAEF slight exceeded 20/1 1 h, respectively. These results suggest optimal conditions for TD are RS/SL, h. Then a couple scale-up experiments were...

Condition monitoring of rolling element bearing is paramount for predicting the lifetime and performing effective maintenance mechanical equipment. To overcome drawbacks hidden Markov model (HMM) improve diagnosis accuracy, conditional random field (CRF) based classifier proposed. In this model, feature vectors sequences fault categories are linked by an undirected graphical in which their relationship represented a global probability distribution. comparison with HMM, main advantage CRF...

In the steel coil manufacturing industry, quality of end face is not only related to product itself, but also directly affects equipment safety downstream production lines. Therefore, detection defects has a pivotal position. This paper proposes SCED-Net (Steel Coil End Detection Network) based on latest YOLO series masterpiece YoloX. this paper, by supplementing data augmentation method, combining proposed multi-information fusion module, while introducing focal loss and soft-nms, achieved...

An elevator fault diagnosis method based on Sequential Probability Ratio Test (SPRT) is proposed in this paper. In order to verify the effectiveness of method, paper designed experiment for mechanical system. Firstly, wavelet transformation used filter noise vibration signal collected experiment. Then kurtosis value filtered extracted as index represent practical status elevator. Finally, SPRT algorithm diagnose faults Experimental results show that has high accuracy applications. It...

In the traditional civil engineering industry, only abstract theoretical concepts are applied to express complex realistic contents, but this method of information transmission is sometimes very limited for participants, because its expression not comprehensive and specific also makes recipients have difficulty in understanding information. The rise development virtual reality (VR) technology has become a good assistant overcome difficulty, providing an extremely effective means displaying...

Vehicle platform vibration (VPV) directly affects the measurement accuracy of precise measuring instrument (PMI) fixed on it. In order to reduce influences VPV accuracy, it is necessary perform isolation between vehicle and PMI. Analysis characteristics a prerequisite for isolation. However, empirical mode decomposition (EMD) ensemble (EEMD) reveal that there obvious mixing phenomenon in collected signals. this paper, noise stretch (NSEEMD) method proposed suppress mixing, specific operation...