To solve the problem of inserting new job into flexible job-shops, this paper proposes a dynamic self-learning artificial bee colony (DSLABC) optimization algorithm to job-shop scheduling (DFJSP). Through reasonable arrangement processing sequence jobs and corresponding relationship between operations machines, makespan can be shortened, economic benefit utilization rate machine improved. Firstly, Q-learning traditional (ABC) are combined form (SLABC) algorithm. Using learning...

Abstract As an important branch of production scheduling, the flexible job shop scheduling problem (FJSP) is a typical NP-hard problem. Researchers have adopted many intelligent algorithms to solve FJSP problem, nonetheless, task dynamically adapting its essential parameters during computational process significant challenge, resulting in solution efficiency and quality failing meet requirements. To this end, paper proposes adaptive gray wolf fast optimization algorithm (SS-GWO), which...

Summary The flexible job‐shop scheduling problem (FJSP) is currently one of the most critical issues in process planning and manufacturing. FJSP studied with goal achieving shortest makespan. Recently, some intelligent optimization algorithms have been applied to solve FJSP, but key parameters cannot be dynamically adjusted during solution process. Thus, solutions best meet needs production. To problems slow convergence speed reaching a local optimum artificial bee colony (ABC) algorithm, an...

In this work, numerical simulations are conducted to reveal the hydrodynamic mechanism of caudal fin propulsion. modeling a bionic fin, universal kinematics model with three degrees freedom is adopted and flexible deformation in spanwise direction considered. Navier-Stokes equations used solve unsteady fluid flow dynamic mesh method applied track locomotion. The force coefficients, torque coefficient, field characteristics extracted analyzed. Then thrust efficiency calculated. order verify...

Quality grading in antler mushroom industrial production is a labor-intensive operation. For long time, manual has been used for grading, which produces various problems such as insufficient reliability, low efficiency, and high body damage. Automatic problem to be solved urgently development with increasing labor costs. To solve the problem, this paper deeply integrates single-stage object detection of YOLOv5 semantic segmentation PSPNet, proposes Y-PNet model real-time an image network....

At present, the sorting of agricultural products in China mainly relies on manual labour, which results low efficiency, and development corresponding automatic equipment lags behind. The grasping method based machine vision has been widely used industry, can provide a reference for products. In this paper, an device was designed. mechanism adopted 4-degree-of-freedom (4-DOF) manipulator, control system monocular camera, realize positioning classification grasp-target. First, geometric model...

To solve the problems of low degree automation, difficulty in quality control and poor working environment during process spray-painting rotational parts, this paper designs an automatic spray monitoring tele-operation system based on digital twin technology, which can realize real-time fault treatment spraying to achieve goal “man-machine isolation”. First, production line for operations is designed equipment be remotely controlled. Then, multiple sensors are used collect environmental...

In view of the miniaturization and decentralization characteristics agricultural equipment factories in China, manufacturing is well suited to cloud model, but there no specific research on services optimization for it. To fill gap, a service method proposed this paper. For dynamic coefficient strategy reliability feedback update are added mathematical model strengthen applicability farming season. As algorithm, artificial ant-bee colony algorithm (DAABA) based ant bee presented. The optimal...

Signed graphs consist of edges and signs, which can be separated into structural information balance-related information, respectively. Existing signed graph neural networks (SGNNs) typically rely on to generate embeddings. Nevertheless, the emergence recent adversarial attacks has had a detrimental impact information. Similar how structure learning restore unsigned graphs, balance applied by improving degree poisoned graph. However, this approach encounters challenge "Irreversibility...

Bionic foils are usually similar in shape to the locomotive organs of animals living fluid media, which is helpful analysis motion mode and hydrodynamic mechanisms biological prototypes. With design underwater vehicles as research background, bionic adopted objects this paper. A geometric model a established depending on prototype. In model, two typical foils―a NACA foil crescent-shaped foil―are chosen objects. Simulations performed using numerical method based computational dynamics...

The smart product represents a new type of products, which contains software and hardware components. Many obsolete products are required to be recycled each year. In the developing countries, inappropriate treatment contaminates natural environment. This study aims coordinate abilities social recycling organisations improve recovery rate waste products. A framework service for is proposed based on concept cloud manufacturing. framework, ontology designed integrate lifecycle data generated...

Agricultural machinery rental is a new service form that uses big data in agriculture to improve the utilization rate of agricultural and promote development economy. To realize scheduling optimization cloud services, dynamic artificial bee-ant colony algorithm (DABAA) proposed solve above problem. First, practicability mathematical model production, coefficient proposed. Then mutation operation combined with bee (ABC) algorithm. Then, iterative threshold adjustment optimal fusion point...

The classification of hidden dangers in urban gas pipelines plays a vital role the smooth operation and solving problem safety pipelines. In recent years, number proportion polyethylene (PE) are increasing day by day, but current is still based on steel pipelines, method highly subjective. Therefore, this paper proposes an improved PLC that integrates use risk matrix compensation coefficient to solve grading PE gas. failure database obtain vulnerability severity consequences when determining...

Based on the backgrounds of underwater propulsors with high hydrodynamic performance, article focuses flapping foils in tandem arrangement and tries to formulate physical mode mathematical model propulsion. Using commercial software Fluent, governing equations are discretized by finite volume method, dynamic mesh method is adopted solve moving boundaries. In order verify validity feasibility performance single foil analyzed. The present results compare well those experimental researches....

The job-shop scheduling problem (JSP) is currently a that affects processing efficiency and economic benefits in large-scale workshops. JSP aims at the optimal completion time, which difficult process arrangement machine allocation problem. Artificial bee colony (ABC) algorithm common to solve JSP. Firstly, this article introduces of scheduling, secondly analyzes principle ABC algorithm, finally verifies effectiveness solving through experiments.

Despite the tremendous success of graph neural networks in learning relational data, it has been widely investigated that are vulnerable to structural attacks on homophilic graphs. Motivated by this, a surge robust models is crafted enhance adversarial robustness However, vulnerability based heterophilic graphs remains mystery us. To bridge this gap, paper, we start explore and theoretically prove update negative classification loss negatively correlated with pairwise similarities powered...