Compressors are important components in various power systems the field of energy and power. In practical applications, compressors often operate under non-design conditions. Therefore, accurate calculation on performance operating conditions is great significance for development application certain equipped with compressors. To calculate predict a compressor all through limited data, interpolation method was combined support vector machine (SVM). Based known data points design conditions,...

Cigarette detection is a crucial component of public safety management. However, detecting such small objects poses significant challenges due to their size and limited feature points. To enhance the accuracy target detection, we propose novel object model, LSOD-YOLOv8 (Lightweight Small Object Detection using YOLOv8). First, introduce lightweight adaptive weight downsampling module in backbone layer YOLOv8 (You Only Look Once version 8), which not only mitigates information loss caused by...

Abstract The objective of this research is to develop a monocular vision system that can locate the positions road lane in real time. First, Canny approach used obtain edge map from image acquired camera mount on vehicle; Second, matching process conducted normalize candidates line; Third, searching method for reinforce potential lines while degraded those impossible ones; Forth, linking condition further enhance confidence lines, and K-means cluster algorithm employed localize lines;...

Planetary gearbox with high speed and precision is important for sophisticated power equipment, the effective sensor data are necessary reliability stability. However, traditional models fault diagnosis of planetary difficult to maintain accuracy effectiveness when amount training scarce. To solve this problem, inspired by deep learning, a novel intelligent method proposed utilizing advantage gated recurrent neural network (RNN) in feature extraction. Moreover, dropout technology introduced...

The axle box in the bogie system of subway trains is a key component connecting primary damper and axle. In order to extract deep features large-scale fault for rapid diagnosis, novel reconstruction characteristics classification method based on residual network with multi-scale stacked receptive field rolling bearings train proposed. Firstly, multi-layer convolutional kernels methods insert them into ultra-deep networks are developed. Then, original vibration signals four acquired...

Accurately estimating the state of health (SOH) lithium-ion batteries (LIBs) is one pivotal technologies to ensure safe and dependable operation electric vehicles (EVs). To tackle challenges related intricate preprocessing procedures extensive data prerequisites conventional SOH estimation approaches, this paper proposes an improved LSTNet network model. Firstly, discharged battery sequence are divided into long-term short-term sequences. A spatially convolutional long memory (ConvLSTM) then...

Abstract System-level remaining useful life (RUL) estimation is difficult due to multiple degrading components, external disturbances, and variable operational conditions. A similarity-based approach does not rely on health assessment more suitable for system-level RUL estimation. However, practical applications, how capture effective degradation features from raw data, fuse nonlinear sensor handle source uncertainties need be considered. To solve the above challenges, this study focuses...

Purpose The purpose of this paper is to compare the combustion characteristics, including pressure, heat release rate (HRR), coefficient variation (COV) indicated mean effective pressure (IMEP), flame development period and duration, aviation kerosene fuel, namely, rocket propellant 3 (RP-3), gasoline on a two-stoke spark ignition engine. Design/methodology/approach This an experimental investigation using bench test reflect performance two-stroke unmanned aerial vehicle (UAV) engine RP-3...

The intelligent transfer diagnosis model is used to address the issue of feature drift caused by changing working conditions rotating parts in engineering. However, few models can perform on multiple unbalanced samples simultaneously, and even fewer visually enhance domain-invariant features, making them more interpretable. To these issues, we propose a novel interpretable Siamese dual attention enhancement compound for samples. diagnose simultaneously consists channel (CFAE) network,...

A bidirectional force feedback dataglove actuated by pneumatic artificial muscles is introduced which has simpler exoskeleton structure and exerts only on the fingertips. Moreover, its fewer attachments can reduce effect of attachment looseness accuracy position control. It meets all needs virtual reality requirement hand rehabilitation as well. Bidirectional movement are achieved producing antagonistic torque with an pair similar to human beings. The support four degrees freedom measurement...

Parameter adjustment is usually applied for designing the proportional-integral-differential (PID) controllers. However, ability to improve control performance by adjusting parameters limited. Hence, with goal achieve ideal closed-loop response, this paper takes advantage of a structural optimization method modifying controller model. A symbolic adaptation algorithm fractional order PID (FOPID) employed obtain precise nonlinear Firstly, modeling comparison duffing system carried out...

Slewing bearing is one of key components in the large size machinery and its remaining useful life (RUL) prediction required to schedule a future action avoid catastrophic events, extend cycles, etc. The vibration-based method has been widely used RUL prediction. However, spurious fluctuation usually exists vibration signal when machines are operated under complex conditions. In order enhance performance model, two kinds new health indicators constructed by spatial-temporal (ST) information...

Lane detection is one of fundamental but critical problems for lane following system intelligent vehicles. However, a robust and cost effective approach still deserve exploit issue. A novel using five steps scheme presents. First, Canny detector used to obtain edge map from the road image acquired monocular camera mount on vehicle; Second, matching process conducted normalize potential candidates line or boundary; Third, searching procession utilized reinforce lines while degraded those...

The construction of health indicators (HI) is an essential task for RUL prognosis. However, the traditional HI methods rely on prior knowledge experts, thus seriously affecting prognosis accuracy RUL. In this paper, a Bi-ConvLSTM model established to adaptively construct corresponding degree performance degradation. Combined with dual index and particle filter algorithm, it applied bearings. Experimental results show that higher than frameworks.