Reliable and quick response fault diagnosis is crucial for the wind turbine generator system (WTGS) to avoid unplanned interruption reduce maintenance cost. However, conditional data generated from WTGS operating in a tough environment always dynamical high-dimensional. To address these challenges, we propose new scheme which composed of multiple extreme learning machines (ELM) hierarchical structure, where forwarding list ELM layers concatenated each them processed independently its...

Acoustic signals are an ideal source of diagnosis data thanks to their intrinsic non-directional coverage, sensitivity incipient defects, and insensitivity structural resonance characteristics. However this makes prevailing signal de-nosing feature extraction methods suffer from high computational cost, low noise ratio (S/N), difficulty extract the compound acoustic emissions for various failure types. To address these challenges, we propose a hybrid processing technique depict embedded...

With the rapid growth of automotive technology, electronically controlled air suspension has been widely used to improve ride comfort and handling stability vehicle by actively modulating stiffness, height, posture. Ride height control (RHC) is main function semi-active suspension, it achieved conducting charging discharging spring, which plays a critical role in improving dynamic performance. In addition, unevenness distribution with payloads at four wheels, different characteristics front...

In response to the need for multiple complete bearing degradation datasets in traditional deep learning networks predict impact on individual bearings, a novel learning-based rolling remaining life prediction method is proposed absence of fully degraded bearng data. This involves processing raw vibration data through Channel-wise Attention Encoder (CAE) from Encoder-Channel (ECA), extracting features related mutual correlation and relevance, selecting desired characteristics, incorporating...

Abstract When using transmission methods to measure the morphology of cylindrical lenses, refraction light at front and rear surfaces lenses often makes it difficult determine path. To address this challenge, paper proposes a phase deflection method based on surface lenses. This involves calculating displacement points with same before after lens is placed in path, then deriving corresponding thickness these from displacement. The feasibility has been verified through simulations....

Abstract Meta-learning has been widely applied and achieved certain results in few-shot cross-domain fault diagnosis due to its powerful generalization robustness. However, existing meta-learning methods mainly focus on within the same machine, ignoring fact that there are more significant domain distribution differences sample imbalance problems between different machines, leading poor diagnostic performance. To address these issues, this paper proposes a semi-supervised prototypical...

Due to the importance of rotating machinery as one most widely used industrial element, development a proper monitoring and fault diagnosis technique prevent malfunction failure machine during operation is necessary. This paper presents method for gearbox based on feature extraction technique, distance evaluation support vector machines (SVMs) ensemble. The consists three stages. Firstly, features raw data are extracted through wavelet packet transform (WPT) time-domain statistical features....

In order to reduce operation and maintenance costs, reliability, quick response capability of multi-fault intelligent diagnosis for the wind turbine system are becoming more important. This paper proposes a rapid data-driven fault diagnostic method, which integrates data pre-processing machine learning techniques. terms pre-processing, features extracted by using proposed modified Hilbert–Huang transforms (HHT) correlation Then, time domain analysis is conducted make feature concise. A...

This study combines signal de-noising, feature extraction, two pairwise-coupled relevance vector machines (PCRVMs) and particle swarm optimization (PSO) for parameter to form an intelligent diagnostic framework gearbox fault detection. Firstly, the noises of sensor signals are de-noised by using wavelet threshold method lower noise level. Then, Hilbert-Huang transform (HHT) energy pattern calculation applied extract features from signals. After that, eleven-dimension vector, which consists...

Incipient damages of wind turbine rolling bearing are very difficult to be detected because the interference multi-frequency components and strong ambient noise. To solve this problem, paper proposes a new method named VMD-AMCKD, combining complementary advantages variational mode decomposition (VMD) adaptive maximum correlated kurtosis deconvolution (AMCKD). A novel index is proposed screen out most sensitive containing fault information after VMD decomposition. The also can determine...

Abstract To address coupling motion issues and realize large constant force range of microgrippers, we present a serial two-degree-of-freedom compliant microgripper (CCFMG) in this paper. output displacement compact structure, Scott–Russell amplification mechanisms, bridge-type lever mechanisms are combined to compensate stroke piezoelectric actuators. In addition, modules utilized achieve output. We investigated CCFMG’s performances by means pseudo-rigid body models finite element analysis....

A reliable fault diagnostic system for gas turbine generator (GTGS), which is complicated and inherent with many types of component faults, essential to avoid the interruption electricity supply. However, GTGS diagnosis faces challenges in terms existence simultaneous-fault high cost acquiring exponentially increased vibration signals constructing system. This research proposes a new framework combining feature extraction, pairwise-coupled probabilistic classifier, decision threshold...

System maintenance for reliable running of key machinery is critical to many industries, where condition monitoring and fault diagnosis important supporting technology. This paper selects a typical component in rotating machinery, the gearbox, as target study proper method prevent malfunction failure. The failure divided into two levels. One at level that includes various gear faults, another system studies statuses include looseness, misalignment unbalance. A prototype built experiment. Two...

Intelligent fault diagnosis of complex machinery is crucial for industries to reduce the maintenance cost and improve prediction performance. Acoustic signal an ideal source because its inherent characteristics in terms being non-directional insensitive structural resonances. However, there are also two main drawbacks acoustic signal, one which low noise ratio (SNR) caused by high sensitivity other computational efficiency huge data size. These would decrease performance system. Therefore,...

Abstract With the continuous development of computer technology, deep learning has been widely used in fault diagnosis and achieved remarkable results. However, actual production, problem insufficient samples difference data domains caused by different working conditions seriously limit improvement model ability. In recent years, meta-learning attracted widespread attention from scholars as one main methods few-shot learning. It can quickly adapt to new tasks training on a small number...

Abstract Mechanical metastructures consisting of periodic cells with adjustable output force charactersitics and ranges have received increasing attention in recent years owing to its unique capability tune mechanical properties such as stiffness Poisson’s ratio etc. In this paper, we present the design, simulation, experimental characterization a metastructure that realizes customized constant output. The consists units are formed by combining positive negative element. Notably, unit also...

This paper proposes a new diagnostic framework, namely, probabilistic committee machine, to diagnose simultaneous-fault in the rotating machinery. The framework combines feature extraction method with ensemble empirical mode decomposition and singular value decomposition, multiple pairwise-coupled sparse Bayesian extreme learning machines (PCSBELM), parameter optimization algorithm create an intelligent framework. is employed find features of single faults pattern. Multiple PCSBELM networks...

Fault diagnosis is very important to maintain the operation of a gas turbine generator system (GTGS) in power plants, where any abnormal situations will interrupt electricity supply. The fault GTGS faces main challenge that acquired data, vibration or sound signals, contain great deal redundant information which extends identification time and degrades diagnostic accuracy. To improve performance GTGS, an effective feature extraction framework proposed solve problem signal disorder signal....