Human-machine interaction (HMI) is a key technology for implementing smart manufacturing, which primarily focuses on the issues of communication, interaction, and cooperation between humans machines. HMI has been widely studied in product lifecycle including design, service, but efficiency safety still cannot meet new requirements manufacturing along with emerging technologies (e.g., big data, artificial intelligence, augmented reality, etc.). Digital twin (DT), as to realize cyber-physical...

This research proposes a novel predictive model to improve the gas prediction accuracy in transformer oil and provide guarantees for accident prevention. First, this study constructs cross-entropy loss function with variable thresholds dynamic weights reduce error transmission deep residual shrinkage network, enhancing sensitivity of normal abnormal states by network. Second, multiobjective particle swarm algorithm random walk strategy are adopted optimize long short-term memory (LSTM)...

Abstract This study proposes a novel method to improve the fault identification performance of transformers. First, couple multiple factors, high‐dimensional feature map composed gas concentrations and some associated variables is constructed. Second, deep residual shrinkage network revised using updated alternating direction multiplier, newly constructed variable soft thresholding proposed eliminate constant deviations. In addition, fast iterative shrinkage‐thresholding algorithm adopted,...

As an enabling technology for smart manufacturing, digital twin has been widely applied in manufacturing shop-floor. A great deal of research focuses on the key issues implementing shop-floor (DTS), including scheduling, production planning, fault diagnosis and prognostics. However, DTS puts forward higher requirements terms real-time interaction. Artificial intelligence (AI), as effective approach to improve physical shop-floor, provides a new method meet above requirements. In this paper,...

Reactive power optimization in system can not only reduce loss, but also improve voltage quality. It is a mixed optimizing question, which its operating variables include the continual and separate, solved process quite complex. The genetic algorithm (GA) used to solve this problem, GA easy fall into local optimum problem with increasing of size, key performance global convergence believed apply algorithms deal diversity population scientifically better tactic searching optimal solution. So...

A novel image fusion network framework with an autonomous encoder and decoder is suggested to increase the visual impression of fused images by improving quality infrared visible light picture fusion.The comprises module, layer, edge improvement module.The module utilizes enhanced Inception for shallow feature extraction, then combines Res2Net Transformer achieve deep-level co-extraction local global features from original picture.An enhancement (EEM) created extract significant features.A...

The main objective of short-term load forecasting (STLF) is to provide predictions for generation scheduling, economic dispatch and security assessment at any time. A new approach designed in this paper the novel method based on cooperative co-evolutionary immune algorithm proposed. network used evolve structure parameters neural network. proposed model has been implemented actual data compared with traditional Radial-Basis Function (RBF) method. test results reveal that possesses far...

This article has been retracted by the publisher.

Analysis the general vehicle routing problem (VRP) of distribution in logistics, and corresponding mathematical model is established. The adaptive hybrid sequences niche artificial fish swarm algorithm (AHSN-AFSA) introduced, study on how to apply solve problem. concept ecological also being introduced order overcome shortcoming traditional obtain optimal solution. Simulation results show that new has solved fast, stable performance so on.

In the rapid development of global market, there is an urgent need for manufacturing enterprises China to provide training its employees ensure their continuous competence in handling task. E-learning systems a variety instructional aids and communication methods, offer learners great flexibility as time place instruction. Given these advantages, it not surprising that business educational institutions are making substantial investments e-learning systems. This paper proposes system...

Dissolved gas analysis (DGA) is an important method to diagnose the fault of power t ransformer. Least squares support vector machine (LS-SVM) has excellent learning, classification ability and generalization ability, which use structural risk minimization instead traditional empirical based on large sample. LS-SVM widely used in pattern recognition function fitting. Kernel parameter selection very decides precision transformer diagnosis. In order enhance diagnosis precision, a new proposed...

An improved strategy particle swarm optimization algorithm is proposed to solve the dynamic load economic dispatch problems in power systems. Many constraints such as ramp rate limits and prohibited zones are taken into account, loss also calculated. On basis of algorithm, a new provided handle make sure particles satisfy constraints. The can guarantee search or around feasible solutions area combined with penalty functions. accuracy speed for will rarely infeasible area, results show that...

A revised strategy particle swarm optimization algorithm is proposed to solve the economic dispatch problems in power systems. Many constraints such as ramp rate limits and prohibited zones are taken into account, loss also calculated. On basis of algorithm, a new provided handle make sure particles satisfy constraints. The can guarantee search or around feasible solutions area combined with penalty functions. various load demand reserve by payment for allocated discussed this paper.

In today's dynamic and highly competitive market environment, the ever changing customer requirements often destabilize master production schedules. It is necessary to analyse effects of any changes in quantities, priorities, due dates, etc., a timely manner incorporate them into revised schedule which must continue be realistic achievable. This paper describes design application knowledge-based system that can used help with creation, testing finalization accurate The test validity...

Monocular depth estimation, enabled by self-supervised learning, is a key technique for 3D perception in computer vision. However, it faces significant challenges real-world scenarios, which encompass adverse weather variations, motion blur, as well scenes with poor lighting conditions at night. Our research reveals that we can divide monocular estimation into three sub-problems: structure consistency, local texture disambiguation, and semantic-structural correlation. approach tackles the...

Map-free relocalization technology is crucial for applications in autonomous navigation and augmented reality, but relying on pre-built maps often impractical. It faces significant challenges due to limitations matching methods the inherent lack of scale monocular images. These issues lead substantial rotational metric errors even localization failures real-world scenarios. Large significantly impact overall process, affecting both translational accuracy. Due camera itself, recovering from a...