Welding quality directly affects the welding structure's service performance and life. Hence, effective monitoring defects is essential to ensure of weld structure. Owing non-uniformity shape, position size defects, it a complicated task analyze evaluate acquired images manually. Fortunately, deep learning has been successfully applied image analysis target recognition. However, use identify time-consuming less accurate due lack adequate training data samples, which easily cause redundancy...

In order to guarantee safe and reliable operation of electric vehicle batteries optimize their energy capacity utilization, it is indispensable estimate state-of-charge (SoC). This study aimed develop a novel estimation approach based on the grey model (GM) genetic algorithms without need high-fidelity battery demanding high computation power. A SoC analytical was established using system theory limited amount incomplete data in contrast with conventional methods. The further improved by...

Battery thermal management (BTM) is essential to ensure the safety of battery pack electric vehicles. For a variety BTM technologies, battery's internal resistance always plays critical role in heat generation rate battery. Many factors (temperature, SOC and discharge rate) impact on resistance, however, scant research has explored effect resistance. This study aims establish multi-factor dynamic model (MF-DIRM) with error compensation strategy accurately estimate In present study, estimated...

The lithium-ion battery plays a crucial role in the power supply of electric vehicles (EVs). Battery remaining useful life (RUL) is critically vital to ensure vehicles' safety and reliability. Due complicated aging mechanism, predicting RUL for management systems (BMSs) challenging. In this article, novel degradation indicator was constructed using information extracted from discharge voltage. reflected complete effective energy voltage signals reveal characteristics. Additionally, an...

Dependable and accurate battery remaining useful life (RUL) prediction is essential for ensuring the safety reliability of systems. To improve dynamic traceability degradation process RUL under different loading profiles, this paper presents an improved method, which established from combination linear optimization resampling particle filter (LORPF) with sliding-window gray model (SGM). Major innovations are presented as follows: (1) increase accuracy prediction, a proposed to overcome...

Battery state-of-health (SoH) monitoring is of great importance to ensure the safety and reliability battery systems. This study proposed an innovative SoH estimation method using hierarchical extreme learning machine (HELM) improve robustness accuracy without complex parameter model was directly applied establish HELM-oriented online framework. First, increase in mean ohmic resistance constructed as a novel health indicator (HI) characterize aging. Then, HI adopted for offline training...

An accurate remaining useful life (RUL) prediction method is significant to optimize the lithium-ion batteries' performances in an intelligent battery management system. Since construction of models and initialization algorithms require a large amount data, it difficult for conventional methods guarantee RUL accuracy when available data are insufficient. To solve this problem, synergy sliding-window grey model (SGM) particle filter (PF) exploited build innovative framework prediction. The...

Abstract Binocular vision measurement benefits from high prediction robustness and low structural complexity. However, there are still significant flaws in its accuracy. In this paper, binocular of a rectangular workpiece is investigated. A new precise method based on designed to achieve dimensions. Firstly, an algorithm for location Zernike moments corner matching proposed employed precisely locate the extract sub-pixel coordinates discrete points image’s edge. Then, novel stereoscopic...

The capacity/state-of-charge (SoC) and voltage of lithium–ion batteries are prime importance in electric vehicles (EVs), so their condition-monitoring techniques extensively studied. This study focuses on the application grey system theory to parameters analysing predicting behaviour during discharge/charge cycles battery. First, Grey relation analysis is applied analyse relationship between capacity/SoC various influencing factors. Second, segment prediction model proposed order test...

Purpose This paper aims to investigate the suppression of end-point vibrations in industrial robot systems that exhibit joint flexibility and are subject external disturbances. Design/methodology/approach The real-time position tracking error is effectively decomposed by using feedforward control based on a dynamic model. Various proportional-derivative controllers adapted versions used compute compensation torque for different errors. approach simultaneously achieve rapid response stability...

X-ray nondestructive testing technology is widely used for inspecting welds and identifying defects, crucial in the manufacturing industry. However, diversity of welding defects imbalanced defect samples reduce classification model accuracy can cause classifier overfitting. This paper proposes an improved DCGAN generating by integrating deep convolutional neural networks to enhance training relationship between generator discriminator, thus increasing number samples. We introduce a...

In the field of abrasive-water-jet polishing technology, influence nozzle geometry on wear and internal-structure erosion in technology is studied, design optimized through experiments a numerical simulation to improve stability efficiency abrasive jet. The mathematical model between cross-sectional area dimensionless length established, as well variation static pressure nozzle. Through Fluent simulation, it found that when 12 mm, abrasive-phase acceleration sufficient intensity minimal....

Accurate and effective battery state-of-health (SoH) monitoring is significant to guarantee the security dependability of electrical equipment. However, adapting SoH estimation methods diverse kinds operating conditions a challenge because intricate deterioration mechanisms batteries. To solve issue, in this article, novel multi-input metabolic long short-term memory (MM-LSTM) framework developed. A degradation state model created with LSTM network describe mechanisms. convey more...

Abstract In actual welding environments, factors such as the process, light intensity, material properties of workpiece, and surface quality introduce interferences noise, reflection, curve around, fume, splash in laser images, which degrade centerline extraction precision weld seam feature point identification. To address these challenges, a comprehensive method for precisely extracting multi-interference environments is proposed. Initially, an adaptive thresholding based on minimum error...