Taihua Zhang

Existing robot end-effectors design methods lack structured domain prior knowledge support and have insufficient interaction with the environment, making it difficult to guarantee the accuracy of the design results. An adaptive design method is proposed that deeply embeds domain knowledge of end effectors into the design process, treats key design parameters as environmental variables, and optimizes them adaptively through reinforcement learning algorithms in perception and feedback. In a simulation environment constructed by combining a knowledge graph, a two-finger translational gripper is used as an example robot end-effector to acquire target data via sensors, and reinforcement learning is used to adaptively optimize the gripper’s key parameters. Experiments are conducted on a simulation platform with three typical tasks, yielding the optimal parameter range. Compared to the proximal policy optimization (PPO) algorithm, which has no prior knowledge input, the knowledge graph embedding proximal policy optimization (KGPPO) algorithm improves the average reward for gripper length and gripper force by 63.96% and 43.09%, respectively, for grasping eggs. The KGPPO algorithm achieves the highest average reward and the best stability compared with other algorithms. Experiments show that this method can significantly improve the efficiency, stability, and accuracy of design parameter optimization.

As one of the major sources of global carbon emissions, the manufacturing industry urgently requires green transformation. The utilization of renewable energy in production workshop offers a promising route toward zero-carbon manufacturing. However, renewable energy fluctuations and dynamic workshop events make efficient scheduling increasingly challenging. This paper introduces a low-carbon and energy-efficient dynamic flexible job shop scheduling problem oriented towards renewable energy integration, and develops a multi-agent deep reinforcement learning framework for dynamic and intelligent production scheduling. Inspired by the Proximal Policy Optimization (PPO) algorithm, a routing agent and a sequencing agent are designed for machine assignment and job sequencing, respectively. Customized state representations and reward functions are also designed to enhance learning performance and scheduling efficiency. Simulation results demonstrate that the proposed method achieves superior performance in multi-objective optimization, effectively balancing production efficiency, energy consumption, and carbon emission reduction across various job shop scheduling scenarios.

In the process of diagnosing the inter-turn short circuit fault of the joint permanent magnet synchronous motor of an industrial robot, due to the small and sparse fault sample data, it is easy to misdiagnose, and it is difficult to quickly and accurately evaluate the fault degree, lock the fault location, and track the fault causes. A multi-task causal knowledge fault diagnosis method for inter-turn short circuits of permanent magnet synchronous motors based on meta-learning is proposed. Firstly, the variation of parameters under the motor’s inter-turn short circuit fault is thoroughly investigated, and the fault characteristic quantity is selected. Comprehensive simulations are conducted using Simulink, Simplorer, and Maxwell to generate data under different inter-turn short circuit fault states; meanwhile, the sample data are accurately labeled. Secondly, the sample data are introduced into the learning network for training, and the multi-task synchronous diagnosis of the fault degree and position of the short circuit between turns is realized. Finally, the Neo4j database based on causality knowledge of motor inter-turn short circuit fault is constructed. Experiments show that this method can diagnose the fault location, fault degree, and fault cause of the motor with different voltage unbalanced degrees. The diagnosis accuracy of fault degree is 99.75 ± 0.25%, and the diagnosis accuracy of fault location and fault degree is 99.45 ± 0.21%.

In the digital twin system of mechatronics engineering, the scale and accuracy of models are continually improving. Nevertheless, this growth can hinder real-time interaction and decision-making accuracy within digital twins. The resulting delay impacts the entire system’s reliability by reducing its response speed and real-time decision-making. Consequently, there is an imperative demand for a lightweight approach to tackle the challenges arising from the escalating scale of digital twin virtual entity models. This paper presents a digital twin methodology that is lightweight. The procedure comprises three primary phases: graph data modeling, graph neural network analysis, and hierarchical simplification of virtual entities. Specifically, the graph neural network method proposed in this article is used to classify the graph data of virtual entities. Then, the model is hierarchically simplified based on the classification. Finally, experiments were conducted on factory and robotic arm datasets to evaluate the proposed method. The experimental results indicate that the DTL-GNN method can reduce system redundancy while preserving the essential features of virtual entities.

The sand cat is a creature suitable for living in the desert. Sand cat swarm optimization (SCSO) is a biomimetic swarm intelligence algorithm, which inspired by the lifestyle of the sand cat. Although the SCSO has achieved good optimization results, it still has drawbacks, such as being prone to falling into local optima, low search efficiency, and limited optimization accuracy due to limitations in some innate biological conditions. To address the corresponding shortcomings, this paper proposes three improved strategies: a novel opposition-based learning strategy, a novel exploration mechanism, and a biological elimination update mechanism. Based on the original SCSO, a multi-strategy improved sand cat swarm optimization (MSCSO) is proposed. To verify the effectiveness of the proposed algorithm, the MSCSO algorithm is applied to two types of problems: global optimization and feature selection. The global optimization includes twenty non-fixed dimensional functions (Dim = 30, 100, and 500) and ten fixed dimensional functions, while feature selection comprises 24 datasets. By analyzing and comparing the mathematical and statistical results from multiple perspectives with several state-of-the-art (SOTA) algorithms, the results show that the proposed MSCSO algorithm has good optimization ability and can adapt to a wide range of optimization problems.