Research on sustainable collaborative scheduling problem of multi-stage mixed flow shop for crankshaft components.

The crankshaft manufacturing process primarily comprises machining, single jacket, and double jacket stages. These stages collectively produce substantial carbon emissions, which significantly impact the environment. Low-carbon energy development and humanity's future are closely related. To promote the sustainable development of crankshaft manufacturing enterprises and improve the production efficiency of crankshafts, research on sustainable collaborative scheduling problems in multi-stage mixed flow shop for crankshaft components is conducted. In addition, the transportation process of related workpieces in the crankshaft manufacturing process, which generally have a large mass, also produces substantial carbon emissions. This paper constructs a multi-objective integer optimization model based on the manufacturing process characteristics of crankshaft components, with minimizing the maximum manufacturing time and carbon emissions as optimization objectives. Considering the complexity of the problem, a comprehensive algorithm integrating moth-flame optimization and NSGA-III is used to solve the mathematical model. Through case experiments, the integrated algorithm is compared and analysed with four classic multi-objective optimization algorithms: NSGA-III, NSGA-II, MOEA/D, and MOPSO. The experiments demonstrate that the algorithm presented in this paper offers significantly enhanced optimization efficiency in solving the problem under study compared to other algorithms. Moreover, this paper compares multi-stage collaborative scheduling and non-collaborative scheduling in the crankshaft manufacturing process, ultimately demonstrating that collaborative scheduling is more conducive to the sustainable development of manufacturing enterprises. The results indicate that the annual carbon emissions can reduce about 3.6 ton.

Research on Teleoperated Virtual Reality Human-Robot Five-Dimensional Collaboration System.

In the realm of industrial robotics, there is a growing challenge in simplifying human-robot collaboration (HRC), particularly in complex settings. The demand for more intuitive teleoperation systems is on the rise. However, optimizing robot control interfaces and streamlining teleoperation remains a formidable task due to the need for operators to possess specialized knowledge and the limitations of traditional methods regarding operational space and time constraints. This study addresses these issues by introducing a virtual reality (VR) HRC system with five-dimensional capabilities. Key advantages of our approach include: (1) real-time observation of robot work, whereby operators can seamlessly monitor the robot's real-time work environment and motion during teleoperation; (2) leveraging VR device capabilities, whereby the strengths of VR devices are harnessed to simplify robot motion control, significantly reducing the learning time for operators; and (3) adaptability across platforms and environments: our system effortlessly adapts to various platforms and working conditions, ensuring versatility across different terminals and scenarios. This system represents a significant advancement in addressing the challenges of HRC, offering improved teleoperation, simplified control, and enhanced accessibility, particularly for operators with limited prior exposure to robot operation. It elevates the overall HRC experience in complex scenarios.

Distributed shop scheduling: A comprehensive review on classifications, models and algorithms.

In the intelligent manufacturing environment, modern industry is developing at a faster pace, and there is an urgent need for reasonable production scheduling to ensure an organized production order and a dependable production guarantee for enterprises. Additionally, production cooperation between enterprises and different branches of enterprises is increasingly common, and distributed manufacturing has become a prevalent production model. In light of these developments, this paper presents the research background and current state of distributed shop scheduling. It summarizes relevant research on issues that align with the new manufacturing model, explores hot topics and concerns and focuses on the classification of distributed parallel machine scheduling, distributed flow shop scheduling, distributed job shop scheduling and distributed assembly shop scheduling. The paper investigates these scheduling problems in terms of single-objective and multi-objective optimization, as well as processing constraints. It also summarizes the relevant optimization algorithms and their limitations. It also provides an overview of research methods and objects, highlighting the development of solution methods and research trends for new problems. Finally, the paper analyzes future research directions in this field.

Application of Fault Diagnosis Method Combining Finite Element Method and Transfer Learning for Insufficient Turbine Rotor Fault Samples.

Deep learning has led to significant progress in the fault diagnosis of mechanical systems. These intelligent models often require large amounts of training data to ensure their generalization capabilities. However, the difficulty of obtaining turbine rotor fault data poses a new challenge for intelligent fault diagnosis. In this study, a turbine rotor fault diagnosis method based on the finite element method and transfer learning (FEMATL) is proposed, ensuring that the intelligent model can maintain high diagnostic accuracy in the case of insufficient samples. This method fully exploits the finite element method (FEM) and transfer learning (TL) for small-sample problems. First, FEM is used to generate data samples with fault information, and then the one-dimensional vibration displacement signal is transformed into a two-dimensional time-frequency diagram (TFD) by taking advantage of the deep learning model to recognize the image. Finally, a pre-trained ResNet18 network was used as the input to carry out transfer learning. The feature extraction layer of the network was trained on the ImageNet dataset and a fully connected layer was used to match the specific classification problems. The experimental results show that the method requires only a small amount of training data to achieve high diagnostic accuracy and significantly reduces the training time.