A new type of riser, such as the thermoplastic composite pipe, features a low mass ratio and is becoming increasingly common in marine engineering projects. However, vortex-induced vibration (VIV) poses significant concern regarding fatigue damage risers, VIV understandings risers with ratios are still limited require further investigation. The present study conducted experimental research on flexible pipe critical 0.50 at subcritical Reynolds numbers (Re) through towing water. displacement...

Based on ensemble empirical mode decomposition (EEMD) and the support vector machine (SVM), an algorithm used in sensor fault detection classification is put forward this paper. Using method through EEMD, signal decomposed into several segments, including original signals, intrinsic functions (IMFs) residual signals. Moreover, as features of fault, their variance, mean, entropy slope are calculated accordance with characteristics different types inherent physical meanings each IMF....

In order to satisfy safety requirements of modern plant-wide processes, multiblocks-based distributed monitoring strategies are often used obtain higher performance, and their two critical issues refer suitable multi-blocks partition for reducing uncertainties local-global fault interpret perception practical physical meaning. To handle these problems, a novel multi-level knowledge-graph (MLKG) based on combining domain experts knowledge data constructed describe characteristics processes....

This paper focuses on reviewing past progress in the advancement of definitions, methods, and models for safety analysis assessment process industrial systems highlighting main research topics. Based knowledge with respect to safety, review covers fact that entire system does not have ability produce casualties, health deterioration, other accidents, which ultimately cause human life threats damage. And, according comparison between reliability, when a is an unreliable state, it must be...

In order to satisfy the safety requirements of plant-wide processes, distributed process monitoring methods are often used. However, few them consider problem on building multilevel knowledge blocks and associations between different blocks, all which beneficial for in avoiding information conflict even improve accuracy. To handle these issues, a method is proposed, based hierarchical graph representation learning with differentiable pooling by using (MLKG). Specifically, MLKG consists...

Modern industrial processes generate many inter-associated variables, which are more likely to implicit associations knowledge for describing irregular changes at different times accurately describe behaviour changes. Motivated by this issue, a novel knowledge-data-based synchronization states analysis method is proposed process monitoring. Its advantage mainly refers integrating physical-chemical mechanism handle the representation of associated relationships between numerous monitor...

This paper introduced a deep learning approach to achieve fault detection with signal analysis and processing, which is based on an sparse auto-encoder can be employed unsupervised automatically extract features of complex data-sets detect fault. from the unrecognized signals intelligent identification. The hidden layer considered as over-complete dictionary, reconstruct input unsupervised. Furthermore, method build up specific architecture describe process industrial system, not only avoid...

This study analyzes bioelectrical signals to achieve automatic epileptic seizure detection. Electroencephalographic (EEG) were recorded with electrodes on healthy, seizure-free, and patients. The challenges in this field are generally regarded be the impacts of non-stationarity nonlinearity EEG signals. To address these challenges, attempts recognize different brain statuses. idea originated from a novel hypothesis that considers as convolution regards itself generation mechanism signals,...

This paper studies features with the characteristic of unknown probability distribution, and its application on fault diagnosis based non-stationary monitoring signals, which mainly consider uncertainty as main factor in masking practical industrial system. Generally, distribution signal feature is prior information trend term lacking. For this reason, different extraction methods, such time-domain, frequency-domain time-frequency-domain have always been used to extract features, they can be...

The increasing prevalence of audio deepfakes poses significant security threats, necessitating robust detection methods. While existing systems exhibit promise, their robustness against malicious manipulations remains underexplored. To bridge the gap, we undertake first comprehensive study susceptibility most widely adopted deepfake detectors to manipulation attacks. Surprisingly, even like volume control can significantly bypass without affecting human perception. address this, propose CLAD...

The intelligent goal of process manufacturing is to achieve high efficiency and greening the entire production. Whereas information system it used functionally independent, resulting knowledge gaps between each level. Decision-making still requires lots workers making manually. industrial metaverse a necessary means bridge by sharing collaborative decision-making. Considering safety stability requirements manufacturing, this article conducts thorough survey on intelligence empowered...

Recent years has witnessed great emerge of online video websites, including the exploded number videos and users. As a result, there appears lot personlized recommender systems. However remain some challenging problems to tackle such as cold start problem, which scientists have made use all kinds sideinformation, e.g. gender, age or comments, release. Currently new type called TSCs (TSC), plays more important role in watching activity. In this paper we utilize TSC recommend for We developed...

Based on our previous paper (Commun. Theor. Phys. 39 (2003) 417) we derive the convolution theorem of fractional Fourier transformation in context quantum mechanics, which seems a convenient and neat way. Generalization this method to complex case is also possible.

At present, there are multiple sets of information systems in substation, which relatively independent, and exist some problems repeated collection, low utilization rate difficult data sharing. These contain not only "four remote" structured data, but also unstructured such as waveform, model graphics. There is no unified storage access interface established hinders the improvement intelligent level advanced applications. To solve above problems, a technology multidimensional historical...